Daily Papers

Although AI systems have been applied in various fields and achieved impressive performance, their safety and reliability are still a big concern. This is especially important for safety-critical tasks. One shared characteristic of these critical tasks is their risk sensitivity, where small mistakes can cause big consequences and even endanger life. There are several factors that could be guidelines for the successful deployment of AI systems in sensitive tasks: (i) failure detection and out-of-distribution (OOD) detection; (ii) overfitting identification; (iii) uncertainty quantification for predictions; (iv) robustness to data perturbations. These factors are also challenges of current AI systems, which are major blocks for building safe and reliable AI. Specifically, the current AI algorithms are unable to identify common causes for failure detection. Furthermore, additional techniques are required to quantify the quality of predictions. All these contribute to inaccurate uncertainty quantification, which lowers trust in predictions. Hence obtaining accurate model uncertainty quantification and its further improvement are challenging. To address these issues, many techniques have been proposed, such as regularization methods and learning strategies. As vision and language are the most typical data type and have many open source benchmark datasets, this thesis will focus on vision-language data processing for tasks like classification, image captioning, and vision question answering. In this thesis, we aim to build a safeguard by further developing current techniques to ensure the accurate model uncertainty for safety-critical tasks.

Ensuring that AI systems reliably and robustly avoid harmful or dangerous behaviours is a crucial challenge, especially for AI systems with a high degree of autonomy and general intelligence, or systems used in safety-critical contexts. In this paper, we will introduce and define a family of approaches to AI safety, which we will refer to as guaranteed safe (GS) AI. The core feature of these approaches is that they aim to produce AI systems which are equipped with high-assurance quantitative safety guarantees. This is achieved by the interplay of three core components: a world model (which provides a mathematical description of how the AI system affects the outside world), a safety specification (which is a mathematical description of what effects are acceptable), and a verifier (which provides an auditable proof certificate that the AI satisfies the safety specification relative to the world model). We outline a number of approaches for creating each of these three core components, describe the main technical challenges, and suggest a number of potential solutions to them. We also argue for the necessity of this approach to AI safety, and for the inadequacy of the main alternative approaches.

A computational ethics framework is essential for AI and autonomous systems operating in complex, real-world environments. Existing approaches often lack the adaptability needed to integrate ethical principles into dynamic and ambiguous contexts, limiting their effectiveness across diverse scenarios. To address these challenges, we outline the necessary ingredients for building a holistic, meta-level framework that combines intermediate representations, probabilistic reasoning, and knowledge representation. The specifications therein emphasize scalability, supporting ethical reasoning at both individual decision-making levels and within the collective dynamics of multi-agent systems. By integrating theoretical principles with contextual factors, it facilitates structured and context-aware decision-making, ensuring alignment with overarching ethical standards. We further explore proposed theorems outlining how ethical reasoners should operate, offering a foundation for practical implementation. These constructs aim to support the development of robust and ethically reliable AI systems capable of navigating the complexities of real-world moral decision-making scenarios.

Developing reliable AI systems to assist human clinicians in multi-modal medical diagnosis has long been a key objective for researchers. Recently, Multi-modal Large Language Models (MLLMs) have gained significant attention and achieved success across various domains. With strong reasoning capabilities and the ability to perform diverse tasks based on user instructions, they hold great potential for enhancing medical diagnosis. However, directly applying MLLMs to the medical domain still presents challenges. They lack detailed perception of visual inputs, limiting their ability to perform quantitative image analysis, which is crucial for medical diagnostics. Additionally, MLLMs often exhibit hallucinations and inconsistencies in reasoning, whereas clinical diagnoses must adhere strictly to established criteria. To address these challenges, we propose MedAgent-Pro, an evidence-based reasoning agentic system designed to achieve reliable, explainable, and precise medical diagnoses. This is accomplished through a hierarchical workflow: at the task level, knowledge-based reasoning generate reliable diagnostic plans for specific diseases following retrieved clinical criteria. While at the case level, multiple tool agents process multi-modal inputs, analyze different indicators according to the plan, and provide a final diagnosis based on both quantitative and qualitative evidence. Comprehensive experiments on both 2D and 3D medical diagnosis tasks demonstrate the superiority and effectiveness of MedAgent-Pro, while case studies further highlight its reliability and interpretability. The code is available at https://github.com/jinlab-imvr/MedAgent-Pro.

Large Language Models (LLMs) struggle with hallucinations and outdated knowledge due to their reliance on static training data. Retrieval-Augmented Generation (RAG) mitigates these issues by integrating external dynamic information enhancing factual and updated grounding. Recent advances in multimodal learning have led to the development of Multimodal RAG, incorporating multiple modalities such as text, images, audio, and video to enhance the generated outputs. However, cross-modal alignment and reasoning introduce unique challenges to Multimodal RAG, distinguishing it from traditional unimodal RAG. This survey offers a structured and comprehensive analysis of Multimodal RAG systems, covering datasets, metrics, benchmarks, evaluation, methodologies, and innovations in retrieval, fusion, augmentation, and generation. We precisely review training strategies, robustness enhancements, and loss functions, while also exploring the diverse Multimodal RAG scenarios. Furthermore, we discuss open challenges and future research directions to support advancements in this evolving field. This survey lays the foundation for developing more capable and reliable AI systems that effectively leverage multimodal dynamic external knowledge bases. Resources are available at https://github.com/llm-lab-org/Multimodal-RAG-Survey.

Precise recognition, editing, and generation of molecules are essential prerequisites for both chemists and AI systems tackling various chemical tasks. We present MolLangBench, a comprehensive benchmark designed to evaluate fundamental molecule-language interface tasks: language-prompted molecular structure recognition, editing, and generation. To ensure high-quality, unambiguous, and deterministic outputs, we construct the recognition tasks using automated cheminformatics tools, and curate editing and generation tasks through rigorous expert annotation and validation. MolLangBench supports the evaluation of models that interface language with different molecular representations, including linear strings, molecular images, and molecular graphs. Evaluations of state-of-the-art models reveal significant limitations: the strongest model (o3) achieves 79.2% and 78.5% accuracy on recognition and editing tasks, which are intuitively simple for humans, and performs even worse on the generation task, reaching only 29.0% accuracy. These results highlight the shortcomings of current AI systems in handling even preliminary molecular recognition and manipulation tasks. We hope MolLangBench will catalyze further research toward more effective and reliable AI systems for chemical applications.

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We systematically investigate and compare the influence of six critical intrinsic model characteristics and three external attack techniques. Our large-scale evaluation is conducted using 32 recent, popular LLMs and LRMs across thirteen distinct model families, spanning a parameter scale from 3B to 235B. The assessment leverages five established safety datasets and probes model vulnerabilities with 56 jailbreak techniques and four CoT attack strategies, resulting in 4.6M API calls. Our key empirical findings are fourfold. First, we identify the LRMs GPT-OSS-20B, Qwen3-Next-80B-A3B-Thinking, and GPT-OSS-120B as the top-three safest models, which substantiates the significant advantage of integrated reasoning and self-reflection mechanisms for robust safety alignment. Second, post-training and knowledge distillation may lead to a systematic degradation of safety alignment. We thus argue that safety must be treated as an explicit constraint or a core optimization objective during these stages, not merely subordinated to the pursuit of general capability. Third, we reveal a pronounced vulnerability: employing a CoT attack via a response prefix can elevate the attack success rate by 3.34x on average and from 0.6% to 96.3% for Seed-OSS-36B-Instruct. This critical finding underscores the safety risks inherent in text-completion interfaces and features that allow user-defined response prefixes in LLM services, highlighting an urgent need for architectural and deployment safeguards. Fourth, roleplay, prompt injection, and gradient-based search for adversarial prompts are the predominant methodologies for eliciting unaligned behaviors in modern models.

The detection of hallucinations in multilingual scientific text generated by Large Language Models (LLMs) presents significant challenges for reliable AI systems. This paper describes our submission to the SHROOM-CAP 2025 shared task on scientific hallucination detection across 9 languages. Unlike most approaches that focus primarily on model architecture, we adopted a data-centric strategy that addressed the critical issue of training data scarcity and imbalance. We unify and balance five existing datasets to create a comprehensive training corpus of 124,821 samples (50% correct, 50% hallucinated), representing a 172x increase over the original SHROOM training data. Our approach fine-tuned XLM-RoBERTa-Large with 560 million parameters on this enhanced dataset, achieves competitive performance across all languages, including 2nd place in Gujarati (zero-shot language) with Factuality F1 of 0.5107, and rankings between 4th-6th place across the remaining 8 languages. Our results demonstrate that systematic data curation can significantly outperform architectural innovations alone, particularly for low-resource languages in zero-shot settings.

Jailbreaking poses a significant risk to the deployment of Large Language Models (LLMs) and Vision Language Models (VLMs). VLMs are particularly vulnerable because they process both text and images, creating broader attack surfaces. However, available resources for jailbreak detection are scarce, particularly in finance. To address this gap, we present FENCE, a bilingual (Korean-English) multimodal dataset for training and evaluating jailbreak detectors in financial applications. FENCE emphasizes domain realism through finance-relevant queries paired with image-grounded threats. Experiments with commercial and open-source VLMs reveal consistent vulnerabilities, with GPT-4o showing measurable attack success rates and open-source models displaying greater exposure. A baseline detector trained on FENCE achieves 99 percent in-distribution accuracy and maintains strong performance on external benchmarks, underscoring the dataset's robustness for training reliable detection models. FENCE provides a focused resource for advancing multimodal jailbreak detection in finance and for supporting safer, more reliable AI systems in sensitive domains. Warning: This paper includes example data that may be offensive.

Recent progress in large language models (LLMs) has led to impressive performance on a range of tasks, yet advanced instruction following (IF)-especially for complex, multi-turn, and system-prompted instructions-remains a significant challenge. Rigorous evaluation and effective training for such capabilities are hindered by the lack of high-quality, human-annotated benchmarks and reliable, interpretable reward signals. In this work, we introduce AdvancedIF (we will release this benchmark soon), a comprehensive benchmark featuring over 1,600 prompts and expert-curated rubrics that assess LLMs ability to follow complex, multi-turn, and system-level instructions. We further propose RIFL (Rubric-based Instruction-Following Learning), a novel post-training pipeline that leverages rubric generation, a finetuned rubric verifier, and reward shaping to enable effective reinforcement learning for instruction following. Extensive experiments demonstrate that RIFL substantially improves the instruction-following abilities of LLMs, achieving a 6.7% absolute gain on AdvancedIF and strong results on public benchmarks. Our ablation studies confirm the effectiveness of each component in RIFL. This work establishes rubrics as a powerful tool for both training and evaluating advanced IF in LLMs, paving the way for more capable and reliable AI systems.

The relentless pursuit of enhancing Large Language Models (LLMs) has led to the advent of Super Retrieval-Augmented Generation (Super RAGs), a novel approach designed to elevate the performance of LLMs by integrating external knowledge sources with minimal structural modifications. This paper presents the integration of Super RAGs into the Mistral 8x7B v1, a state-of-the-art LLM, and examines the resultant improvements in accuracy, speed, and user satisfaction. Our methodology uses a fine-tuned instruct model setup and a cache tuning fork system, ensuring efficient and relevant data retrieval. The evaluation, conducted over several epochs, demonstrates significant enhancements across all metrics. The findings suggest that Super RAGs can effectively augment LLMs, paving the way for more sophisticated and reliable AI systems. This research contributes to the field by providing empirical evidence of the benefits of Super RAGs and offering insights into their potential applications.

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they often struggle with spatial reasoning. This paper presents a novel neural-symbolic framework that enhances LLMs' spatial reasoning abilities through iterative feedback between LLMs and Answer Set Programming (ASP). We evaluate our approach on two benchmark datasets: StepGame and SparQA, implementing three distinct strategies: (1) direct prompting baseline, (2) Facts+Rules prompting, and (3) DSPy-based LLM+ASP pipeline with iterative refinement. Our experimental results demonstrate that the LLM+ASP pipeline significantly outperforms baseline methods, achieving an average 82% accuracy on StepGame and 69% on SparQA, marking improvements of 40-50% and 8-15% respectively over direct prompting. The success stems from three key innovations: (1) effective separation of semantic parsing and logical reasoning through a modular pipeline, (2) iterative feedback mechanism between LLMs and ASP solvers that improves program rate, and (3) robust error handling that addresses parsing, grounding, and solving failures. Additionally, we propose Facts+Rules as a lightweight alternative that achieves comparable performance on complex SparQA dataset, while reducing computational overhead.Our analysis across different LLM architectures (Deepseek, Llama3-70B, GPT-4.0 mini) demonstrates the framework's generalizability and provides insights into the trade-offs between implementation complexity and reasoning capability, contributing to the development of more interpretable and reliable AI systems.

The rapid evolution of generative AI necessitates robust safety evaluations. However, current safety datasets are predominantly English-centric, failing to capture specific risks in non-English, socio-cultural contexts such as Korean, and are often limited to the text modality. To address this gap, we introduce AssurAI, a new quality-controlled Korean multimodal dataset for evaluating the safety of generative AI. First, we define a taxonomy of 35 distinct AI risk factors, adapted from established frameworks by a multidisciplinary expert group to cover both universal harms and relevance to the Korean socio-cultural context. Second, leveraging this taxonomy, we construct and release AssurAI, a large-scale Korean multimodal dataset comprising 11,480 instances across text, image, video, and audio. Third, we apply the rigorous quality control process used to ensure data integrity, featuring a two-phase construction (i.e., expert-led seeding and crowdsourced scaling), triple independent annotation, and an iterative expert red-teaming loop. Our pilot study validates AssurAI's effectiveness in assessing the safety of recent LLMs. We release AssurAI to the public to facilitate the development of safer and more reliable generative AI systems for the Korean community.

Cutting-edge agentic AI systems are built on foundation models that can be adapted to plan, reason, and interact with external tools to perform increasingly complex and specialized tasks. As these systems grow in capability and scope, adaptation becomes a central mechanism for improving performance, reliability, and generalization. In this paper, we unify the rapidly expanding research landscape into a systematic framework that spans both agent adaptations and tool adaptations. We further decompose these into tool-execution-signaled and agent-output-signaled forms of agent adaptation, as well as agent-agnostic and agent-supervised forms of tool adaptation. We demonstrate that this framework helps clarify the design space of adaptation strategies in agentic AI, makes their trade-offs explicit, and provides practical guidance for selecting or switching among strategies during system design. We then review the representative approaches in each category, analyze their strengths and limitations, and highlight key open challenges and future opportunities. Overall, this paper aims to offer a conceptual foundation and practical roadmap for researchers and practitioners seeking to build more capable, efficient, and reliable agentic AI systems.

Flawed planning from VLM-driven embodied agents poses significant safety hazards, hindering their deployment in real-world household tasks. However, existing static, non-interactive evaluation paradigms fail to adequately assess risks within these interactive environments, since they cannot simulate dynamic risks that emerge from an agent's actions and rely on unreliable post-hoc evaluations that ignore unsafe intermediate steps. To bridge this critical gap, we propose evaluating an agent's interactive safety: its ability to perceive emergent risks and execute mitigation steps in the correct procedural order. We thus present IS-Bench, the first multi-modal benchmark designed for interactive safety, featuring 161 challenging scenarios with 388 unique safety risks instantiated in a high-fidelity simulator. Crucially, it facilitates a novel process-oriented evaluation that verifies whether risk mitigation actions are performed before/after specific risk-prone steps. Extensive experiments on leading VLMs, including the GPT-4o and Gemini-2.5 series, reveal that current agents lack interactive safety awareness, and that while safety-aware Chain-of-Thought can improve performance, it often compromises task completion. By highlighting these critical limitations, IS-Bench provides a foundation for developing safer and more reliable embodied AI systems.

Large Language Models (LLMs), despite advances in safety alignment, remain vulnerable to jailbreak attacks designed to circumvent protective mechanisms. Prevailing defense strategies rely on external interventions, such as input filtering or output modification, which often lack generalizability and compromise model utility while incurring significant computational overhead. In this work, we introduce a new, training-free defense paradigm, Self-Activating Internal Defense (SAID), which reframes the defense task from external correction to internal capability activation. SAID uniquely leverages the LLM's own reasoning abilities to proactively identify and neutralize malicious intent through a three-stage pipeline: model-native intent distillation to extract core semantics, optimal safety prefix probing to activate latent safety awareness, and a conservative aggregation strategy to ensure robust decision-making. Extensive experiments on five open-source LLMs against six advanced jailbreak attacks demonstrate that SAID substantially outperforms state-of-the-art defenses in reducing harmful outputs. Crucially, it achieves this while preserving model performance on benign tasks and incurring minimal computational overhead. Our work establishes that activating the intrinsic safety mechanisms of LLMs is a more robust and scalable path toward building safer and more reliable aligned AI systems.

Hallucination has been a major problem for large language models and remains a critical challenge when it comes to multimodality in which vision-language models (VLMs) have to deal with not just textual but also visual inputs. Despite rapid progress in VLMs, resources for evaluating and addressing multimodal hallucination are limited and mostly focused on evaluation. This work introduces HaloQuest, a novel visual question answering dataset that captures various aspects of multimodal hallucination such as false premises, insufficient contexts, and visual challenges. A novel idea from HaloQuest is to leverage synthetic images, apart from real ones, to enable dataset creation at scale. With over 7.7K examples spanning across a wide variety of categories, HaloQuest was designed to be both a challenging benchmark for VLMs and a fine-tuning dataset for advancing multimodal reasoning. Our experiments reveal that current models struggle with HaloQuest, with all open-source VLMs achieving below 36% accuracy. On the other hand, fine-tuning on HaloQuest significantly reduces hallucination rates while preserving performance on standard reasoning tasks. Our results discover that benchmarking with generated images is highly correlated (r=0.97) with real images. Last but not least, we propose a novel Auto-Eval mechanism that is highly correlated with human raters (r=0.99) for evaluating VLMs. In sum, this work makes concrete strides towards understanding, evaluating, and mitigating hallucination in VLMs, serving as an important step towards more reliable multimodal AI systems in the future.

Surgical triplet detection has emerged as a pivotal task in surgical video analysis, with significant implications for performance assessment and the training of novice surgeons. However, existing datasets such as CholecT50 exhibit critical limitations: they lack precise spatial bounding box annotations, provide inconsistent and clinically ungrounded temporal labels, and rely on a single data source, which limits model generalizability.To address these shortcomings, we introduce ProstaTD, a large-scale, multi-institutional dataset for surgical triplet detection, developed from the technically demanding domain of robot-assisted prostatectomy. ProstaTD offers clinically defined temporal boundaries and high-precision bounding box annotations for each structured triplet action. The dataset comprises 60,529 video frames and 165,567 annotated triplet instances, collected from 21 surgeries performed across multiple institutions, reflecting a broad range of surgical practices and intraoperative conditions. The annotation process was conducted under rigorous medical supervision and involved more than 50 contributors, including practicing surgeons and medically trained annotators, through multiple iterative phases of labeling and verification. ProstaTD is the largest and most diverse surgical triplet dataset to date, providing a robust foundation for fair benchmarking, the development of reliable surgical AI systems, and scalable tools for procedural training.

Vision-Language Models (VLMs) have shown strong visual understanding and are increasingly deployed in embodied AI systems, where reliable perception under real conditions is essential. However, existing benchmarks assess VLMs using clean images or isolated perturbations rather than stresses caused by physical scene formation. This design has two limitations: it covers only a narrow subset of everyday visual stresses, and some perturbations rarely appear in realistic embodied scenes. This gap raises a fundamental question: how can we define visual stress in a principled way that captures the diverse factors encountered in physical environments? To address this question, we formulate visual perception from an inverse graphics perspective and introduce RoboStressBench, a benchmark for evaluating VLM robustness to physical visual stress in embodied scenes. Inspired by the physical rendering equation, RoboStressBench decomposes visual stress into four physically grounded dimensions: Material (M), Viewpoint (V), Lighting (L), and Geometry (G). This design enables RoboStressBench to cover a broad range of visual stresses in real-world environments, while allowing controlled analysis of their effects on VLM capabilities such as visual recognition, reasoning, and planning. Through comprehensive evaluations of state-of-the-art VLMs, we identify stress-specific failure modes and reveal that different physical factors degrade different embodied capabilities, which are often obscured by aggregate accuracy. We further introduce a stress-aware agentic solver that detects visual stressors and invokes visual-editing skills before reasoning, improving robustness in high-stress scenarios. Overall, RoboStressBench provides a principled evaluation framework for diagnosing and improving VLM perception under real-world physical stress, supporting the development of more reliable embodied AI systems.

We introduce KFinEval-Pilot, a benchmark suite specifically designed to evaluate large language models (LLMs) in the Korean financial domain. Addressing the limitations of existing English-centric benchmarks, KFinEval-Pilot comprises over 1,000 curated questions across three critical areas: financial knowledge, legal reasoning, and financial toxicity. The benchmark is constructed through a semi-automated pipeline that combines GPT-4-generated prompts with expert validation to ensure domain relevance and factual accuracy. We evaluate a range of representative LLMs and observe notable performance differences across models, with trade-offs between task accuracy and output safety across different model families. These results highlight persistent challenges in applying LLMs to high-stakes financial applications, particularly in reasoning and safety. Grounded in real-world financial use cases and aligned with the Korean regulatory and linguistic context, KFinEval-Pilot serves as an early diagnostic tool for developing safer and more reliable financial AI systems.

Large language models (LLMs) are being rapidly integrated into decision-support tools, automation workflows, and AI-enabled software systems. However, their behavior in production environments remains poorly understood, and their failure patterns differ fundamentally from those of traditional machine learning models. This paper presents a system-level taxonomy of fifteen hidden failure modes that arise in real-world LLM applications, including multi-step reasoning drift, latent inconsistency, context-boundary degradation, incorrect tool invocation, version drift, and cost-driven performance collapse. Using this taxonomy, we analyze the growing gap in evaluation and monitoring practices: existing benchmarks measure knowledge or reasoning but provide little insight into stability, reproducibility, drift, or workflow integration. We further examine the production challenges associated with deploying LLMs - including observability limitations, cost constraints, and update-induced regressions - and outline high-level design principles for building reliable, maintainable, and cost-aware LLM systems. Finally, we outline high-level design principles for building reliable, maintainable, and cost-aware LLM-based systems. By framing LLM reliability as a system-engineering problem rather than a purely model-centric one, this work provides an analytical foundation for future research on evaluation methodology, AI system robustness, and dependable LLM deployment.

Aligning large language models with human preferences is critical for creating reliable and controllable AI systems. A human preference can be visualized as a high-dimensional vector where different directions represent trade-offs between desired attributes (e.g., helpfulness vs. verbosity). Yet, because the training data often reflects dominant, average preferences, LLMs tend to perform well on common requests but fall short in specific, individual needs. This mismatch creates a preference coverage gap. Existing methods often address this through costly retraining, which may not be generalized to the full spectrum of diverse preferences. This brittleness means that when a user's request reflects a nuanced preference deviating from the training data's central tendency, model performance can degrade unpredictably. To address this challenge, we introduce Robust Preference Selection (RPS), a post-hoc, training-free method by leveraging directional neighborhood consensus. Instead of forcing a model to generate a response from a single, highly specific preference, RPS samples multiple responses from a local neighborhood of related preferences to create a superior candidate pool. It then selects the response that best aligns with the user's original intent. We provide a theoretical framework showing our neighborhood generation strategy is provably superior to a strong baseline that also samples multiple candidates. Comprehensive experiments across three distinct alignment paradigms (DPA, DPO, and SFT) demonstrate that RPS consistently improves robustness against this baseline, achieving win rates of up to 69% on challenging preferences from under-represented regions of the space without any model retraining. Our work presents a practical, theoretically-grounded solution for enhancing the reliability of preference-aligned models.

Large Language Models (LLMs), despite their advanced linguistic capabilities, fundamentally lack an intuitive understanding of physical dynamics, which limits their effectiveness in real-world scenarios that require causal reasoning. In this paper, we introduce Causal World Model Induction (CWMI), a novel framework designed to embed an explicit model of causal physics within an LLM. Our approach incorporates a dedicated Causal Physics Module (CPM) and a new training objective called Causal Intervention Loss, encouraging the model to learn cause-and-effect relationships from multimodal data. By training the model to predict the outcomes of hypothetical interventions instead of merely capturing statistical correlations, CWMI develops a robust internal representation of physical laws. Experimental results show that CWMI significantly outperforms state-of-the-art LLMs on zero-shot physical reasoning tasks, including the PIQA benchmark and our newly proposed PhysiCa-Bench dataset. These findings demonstrate that inducing a causal world model is a critical step toward more reliable and generalizable AI systems.

We present Azimuth, an open-source and easy-to-use tool to perform error analysis for text classification. Compared to other stages of the ML development cycle, such as model training and hyper-parameter tuning, the process and tooling for the error analysis stage are less mature. However, this stage is critical for the development of reliable and trustworthy AI systems. To make error analysis more systematic, we propose an approach comprising dataset analysis and model quality assessment, which Azimuth facilitates. We aim to help AI practitioners discover and address areas where the model does not generalize by leveraging and integrating a range of ML techniques, such as saliency maps, similarity, uncertainty, and behavioral analyses, all in one tool. Our code and documentation are available at github.com/servicenow/azimuth.

Hallucination remains a critical challenge for deploying Large Language Models (LLMs) in finance. Accurate extraction and precise calculation from tabular data are essential for reliable financial analysis, since even minor numerical errors can undermine decision-making and regulatory compliance. Financial applications have unique requirements, often relying on context-dependent, numerical, and proprietary tabular data that existing hallucination benchmarks rarely capture. In this study, we develop a rigorous and scalable framework for evaluating intrinsic hallucinations in financial LLMs, conceptualized as a context-aware masked span prediction task over real-world financial documents. Our main contributions are: (1) a novel, automated dataset creation paradigm using a masking strategy; (2) a new hallucination evaluation dataset derived from S&P 500 annual reports; and (3) a comprehensive evaluation of intrinsic hallucination patterns in state-of-the-art LLMs on financial tabular data. Our work provides a robust methodology for in-house LLM evaluation and serves as a critical step toward building more trustworthy and reliable financial Generative AI systems.

Hallucinations in generative AI, particularly in Large Language Models (LLMs), pose a significant challenge to the reliability of multilingual applications. Existing benchmarks for hallucination detection focus primarily on English and a few widely spoken languages, lacking the breadth to assess inconsistencies in model performance across diverse linguistic contexts. To address this gap, we introduce Poly-FEVER, a large-scale multilingual fact verification benchmark specifically designed for evaluating hallucination detection in LLMs. Poly-FEVER comprises 77,973 labeled factual claims spanning 11 languages, sourced from FEVER, Climate-FEVER, and SciFact. It provides the first large-scale dataset tailored for analyzing hallucination patterns across languages, enabling systematic evaluation of LLMs such as ChatGPT and the LLaMA series. Our analysis reveals how topic distribution and web resource availability influence hallucination frequency, uncovering language-specific biases that impact model accuracy. By offering a multilingual benchmark for fact verification, Poly-FEVER facilitates cross-linguistic comparisons of hallucination detection and contributes to the development of more reliable, language-inclusive AI systems. The dataset is publicly available to advance research in responsible AI, fact-checking methodologies, and multilingual NLP, promoting greater transparency and robustness in LLM performance. The proposed Poly-FEVER is available at: https://huggingface.co/datasets/HanzhiZhang/Poly-FEVER.

Domain expertise enhances judgment within boundaries but creates systematic vulnerabilities specifically at borders. We term this Transitive Expert Error (TEE), distinct from Dunning-Kruger effects, requiring calibrated expertise as precondition. Mechanisms enabling reliable within-domain judgment become liabilities when structural similarity masks causal divergence. Two core mechanisms operate: structural similarity bias causes experts to overweight surface features (shared vocabulary, patterns, formal structure) while missing causal architecture differences; authority persistence maintains confidence across competence boundaries through social reinforcement and metacognitive failures (experts experience no subjective uncertainty as pattern recognition operates smoothly on familiar-seeming inputs.) These mechanism intensify under three conditions: shared vocabulary masking divergent processes, social pressure for immediate judgment, and delayed feedback. These findings extend to AI routing architectures (MoE systems, multi-model orchestration, tool-using agents, RAG systems) exhibiting routing-induced failures (wrong specialist selected) and coverage-induced failures (no appropriate specialist exists). Both produce a hallucination phenotype: confident, coherent, structurally plausible but causally incorrect outputs at domain boundaries. In human systems where mechanisms are cognitive black boxes; AI architectures make them explicit and addressable. We propose interventions: multi-expert activation with disagreement detection (router level), boundary-aware calibration (specialist level), and coverage gap detection (training level). TEE has detectable signatures (routing patterns, confidence-accuracy dissociations, domain-inappropriate content) enabling monitoring and mitigation. What remains intractable in human cognition becomes addressable through architectural design.

We introduce Paper2Agent, an automated framework that converts research papers into AI agents. Paper2Agent transforms research output from passive artifacts into active systems that can accelerate downstream use, adoption, and discovery. Conventional research papers require readers to invest substantial effort to understand and adapt a paper's code, data, and methods to their own work, creating barriers to dissemination and reuse. Paper2Agent addresses this challenge by automatically converting a paper into an AI agent that acts as a knowledgeable research assistant. It systematically analyzes the paper and the associated codebase using multiple agents to construct a Model Context Protocol (MCP) server, then iteratively generates and runs tests to refine and robustify the resulting MCP. These paper MCPs can then be flexibly connected to a chat agent (e.g. Claude Code) to carry out complex scientific queries through natural language while invoking tools and workflows from the original paper. We demonstrate Paper2Agent's effectiveness in creating reliable and capable paper agents through in-depth case studies. Paper2Agent created an agent that leverages AlphaGenome to interpret genomic variants and agents based on ScanPy and TISSUE to carry out single-cell and spatial transcriptomics analyses. We validate that these paper agents can reproduce the original paper's results and can correctly carry out novel user queries. By turning static papers into dynamic, interactive AI agents, Paper2Agent introduces a new paradigm for knowledge dissemination and a foundation for the collaborative ecosystem of AI co-scientists.

While theories of discourse and cognitive science have long recognized the value of unhurried pacing, recent dialogue research tends to minimize friction in conversational systems. Yet, frictionless dialogue risks fostering uncritical reliance on AI outputs, which can obscure implicit assumptions and lead to unintended consequences. To meet this challenge, we propose integrating positive friction into conversational AI, which promotes user reflection on goals, critical thinking on system response, and subsequent re-conditioning of AI systems. We hypothesize systems can improve goal alignment, modeling of user mental states, and task success by deliberately slowing down conversations in strategic moments to ask questions, reveal assumptions, or pause. We present an ontology of positive friction and collect expert human annotations on multi-domain and embodied goal-oriented corpora. Experiments on these corpora, along with simulated interactions using state-of-the-art systems, suggest incorporating friction not only fosters accountable decision-making, but also enhances machine understanding of user beliefs and goals, and increases task success rates.

Mental health disorders are rising worldwide. However, the availability of trained clinicians has not scaled proportionally, leaving many people without adequate or timely support. To bridge this gap, recent studies have shown the promise of Artificial Intelligence (AI) to assist mental health diagnosis, monitoring, and intervention. However, the development of efficient, reliable, and ethical AI to assist clinicians is heavily dependent on high-quality clinical training datasets. Despite growing interest in data curation for training clinical AI assistants, existing datasets largely remain scattered, under-documented, and often inaccessible, hindering the reproducibility, comparability, and generalizability of AI models developed for clinical mental health care. In this paper, we present the first comprehensive survey of clinical mental health datasets relevant to the training and development of AI-powered clinical assistants. We categorize these datasets by mental disorders (e.g., depression, schizophrenia), data modalities (e.g., text, speech, physiological signals), task types (e.g., diagnosis prediction, symptom severity estimation, intervention generation), accessibility (public, restricted or private), and sociocultural context (e.g., language and cultural background). Along with these, we also investigate synthetic clinical mental health datasets. Our survey identifies critical gaps such as a lack of longitudinal data, limited cultural and linguistic representation, inconsistent collection and annotation standards, and a lack of modalities in synthetic data. We conclude by outlining key challenges in curating and standardizing future datasets and provide actionable recommendations to facilitate the development of more robust, generalizable, and equitable mental health AI systems.

As AI systems become more integrated into daily life, the need for safer and more reliable moderation has never been greater. Large Language Models (LLMs) have demonstrated remarkable capabilities, surpassing earlier models in complexity and performance. Their evaluation across diverse tasks has consistently showcased their potential, enabling the development of adaptive and personalized agents. However, despite these advancements, LLMs remain prone to errors, particularly in areas requiring nuanced moral reasoning. They struggle with detecting implicit hate, offensive language, and gender biases due to the subjective and context-dependent nature of these issues. Moreover, their reliance on training data can inadvertently reinforce societal biases, leading to inconsistencies and ethical concerns in their outputs. To explore the limitations of LLMs in this role, we developed an experimental framework based on state-of-the-art (SOTA) models to assess human emotions and offensive behaviors. The framework introduces a unified benchmark dataset encompassing 49 distinct categories spanning the wide spectrum of human emotions, offensive and hateful text, and gender and racial biases. Furthermore, we introduced SafePhi, a QLoRA fine-tuned version of Phi-4, adapting diverse ethical contexts and outperforming benchmark moderators by achieving a Macro F1 score of 0.89, where OpenAI Moderator and Llama Guard score 0.77 and 0.74, respectively. This research also highlights the critical domains where LLM moderators consistently underperformed, pressing the need to incorporate more heterogeneous and representative data with human-in-the-loop, for better model robustness and explainability.

In Agentic AI, Large Language Models (LLMs) are increasingly used in the orchestration layer to coordinate multiple agents and to interact with external services, retrieval components, and shared memory. In this setting, failures are not limited to incorrect final outputs. They also arise from long-horizon interaction, stochastic decisions, and external side effects (such as API calls, database writes, and message sends). Common failures include non-termination, role drift, propagation of unsupported claims, and attacks via untrusted context or external channels. This paper presents an assurance framework for such Agentic AI systems. Executions are instrumented as Message-Action Traces (MAT) with explicit step and trace contracts. Contracts provide machine-checkable verdicts, localize the first violating step, and support deterministic replay. The framework includes stress testing, formulated as a budgeted counterexample search over bounded perturbations. It also supports structured fault injection at service, retrieval, and memory boundaries to assess containment under realistic operational faults and degraded conditions. Finally, governance is treated as a runtime component, enforcing per-agent capability limits and action mediation (allow, rewrite, block) at the language-to-action boundary. To support comparative evaluations across stochastic seeds, models, and orchestration configurations, the paper defines trace-based metrics for task success, termination reliability, contract compliance, factuality indicators, containment rate, and governance outcome distributions. More broadly, the framework is intended as a common abstraction to support testing and evaluation of multi-agent LLM systems, and to facilitate reproducible comparison across orchestration designs and configurations.

Agentic AI marks a major shift in how autonomous systems reason, plan, and execute multi-step tasks. Unlike traditional single model prompting, agentic workflows integrate multiple specialized agents with different Large Language Models(LLMs), tool-augmented capabilities, orchestration logic, and external system interactions to form dynamic pipelines capable of autonomous decision-making and action. As adoption accelerates across industry and research, organizations face a central challenge: how to design, engineer, and operate production-grade agentic AI workflows that are reliable, observable, maintainable, and aligned with safety and governance requirements. This paper provides a practical, end-to-end guide for designing, developing, and deploying production-quality agentic AI systems. We introduce a structured engineering lifecycle encompassing workflow decomposition, multi-agent design patterns, Model Context Protocol(MCP), and tool integration, deterministic orchestration, Responsible-AI considerations, and environment-aware deployment strategies. We then present nine core best practices for engineering production-grade agentic AI workflows, including tool-first design over MCP, pure-function invocation, single-tool and single-responsibility agents, externalized prompt management, Responsible-AI-aligned model-consortium design, clean separation between workflow logic and MCP servers, containerized deployment for scalable operations, and adherence to the Keep it Simple, Stupid (KISS) principle to maintain simplicity and robustness. To demonstrate these principles in practice, we present a comprehensive case study: a multimodal news-analysis and media-generation workflow. By combining architectural guidance, operational patterns, and practical implementation insights, this paper offers a foundational reference to build robust, extensible, and production-ready agentic AI workflows.

The rapid advancement of large language models (LLMs) has significantly impacted various domains, including healthcare and biomedicine. However, the phenomenon of hallucination, where LLMs generate outputs that deviate from factual accuracy or context, poses a critical challenge, especially in high-stakes domains. This paper conducts a scoping study of existing techniques for mitigating hallucinations in knowledge-based task in general and especially for medical domains. Key methods covered in the paper include Retrieval-Augmented Generation (RAG)-based techniques, iterative feedback loops, supervised fine-tuning, and prompt engineering. These techniques, while promising in general contexts, require further adaptation and optimization for the medical domain due to its unique demands for up-to-date, specialized knowledge and strict adherence to medical guidelines. Addressing these challenges is crucial for developing trustworthy AI systems that enhance clinical decision-making and patient safety as well as accuracy of biomedical scientific research.

Artificial intelligence (AI) developers are increasingly building language models with warm and empathetic personas that millions of people now use for advice, therapy, and companionship. Here, we show how this creates a significant trade-off: optimizing language models for warmth undermines their reliability, especially when users express vulnerability. We conducted controlled experiments on five language models of varying sizes and architectures, training them to produce warmer, more empathetic responses, then evaluating them on safety-critical tasks. Warm models showed substantially higher error rates (+10 to +30 percentage points) than their original counterparts, promoting conspiracy theories, providing incorrect factual information, and offering problematic medical advice. They were also significantly more likely to validate incorrect user beliefs, particularly when user messages expressed sadness. Importantly, these effects were consistent across different model architectures, and occurred despite preserved performance on standard benchmarks, revealing systematic risks that current evaluation practices may fail to detect. As human-like AI systems are deployed at an unprecedented scale, our findings indicate a need to rethink how we develop and oversee these systems that are reshaping human relationships and social interaction.

AI systems deployed in legal workflows hallucinate at rates that aggregate metrics report at ~52%, but this average conceals where errors concentrate and in which direction they run, leaving compliance officers without an actionable signal for trustworthy deployment. We present LegalHalluLens, an auditing framework with three components: typed hallucination profiles across four legally-motivated claim categories (numeric, temporal, obligation/entitlement, factual) over CUAD (Hendrycks et al., 2021); a Risk Direction Index (RDI) that reduces omission-versus-invention bias to a single deployment-comparable scalar; and a typed debate pipeline calibrated to both magnitudes and directions. Across 510 contracts and 249,252 clause-level instances we measure a within-model gap of approximately 38-40 pp between obligation/numeric and temporal claims that aggregate reporting hides, and show that two systems with matched 52% rates can carry opposite RDIs. The debate pipeline reduces fabricated detections by 45% with per-category gains tracking the diagnosis, matching commercial APIs with a substantially smaller backbone (4B active parameters). Typed profiles and RDI surface failure modes that aggregate metrics hide; we further show these diagnostics serve as calibration inputs for multi-agent debate pipelines, where Skeptic challenges and asymmetric gates targeted at measured failure modes outperform generically-tuned debate. The framework supports direction-aware procurement, accountability, and agent design for legal AI deployed in the wild.

Function-calling language models are essential for agentic AI systems that translate natural language into executable structured actions, yet existing models exhibit severe structural instability when applied to Arabic. We present AISA-AR-FunctionCall, a production-oriented Arabic function-calling framework built on a 270M-parameter FunctionGemma backbone and trained through systematic dataset auditing, schema repair, tool-aware prompt restructuring, and full-parameter supervised fine-tuning. On a held-out test set, fine-tuning reduces parse failures from 87\% to below 1\%, improves function name accuracy by more than eightfold, and substantially enhances argument alignment across dialects and domains. Error analysis reveals a transition from structural collapse to semantic misalignment, suggesting that serialization stability and decision-level reasoning are separable challenges. We further explore a reasoning-augmented LoRA variant that introduces explicit intermediate reasoning prior to tool invocation. All datasets and models are publicly released under the AISA framework.

Current large language models (LLMs) excel in verifiable domains where outputs can be checked before action but prove less reliable for high-stakes strategic decisions with uncertain outcomes. This gap, driven by mutually reinforcing cognitive biases in both humans and artificial intelligence (AI) systems, threatens the defensibility of valuations and sustainability of investments in the sector. This report describes a framework emerging from systematic qualitative assessment across 7 frontier-grade LLMs and 3 market-facing venture vignettes under time pressure. Detailed prompting specifying decision partnership and explicitly instructing avoidance of sycophancy, confabulation, solution drift, and nihilism achieved initial partnership state but failed to maintain it under operational pressure. Sustaining protective partnership state required an emergent 7-stage calibration sequence, built upon a 4-stage initialization process, within a 5-layer protection architecture enabling bias self-monitoring, human-AI adversarial challenge, partnership state verification, performance degradation detection, and stakeholder protection. Three discoveries resulted: partnership state is achievable through ordered calibration but requires emergent maintenance protocols; reliability degrades when architectural drift and context exhaustion align; and dissolution discipline prevents costly pursuit of fundamentally wrong directions. Cross-model validation revealed systematic performance differences across LLM architectures. This approach demonstrates that human-AI teams can achieve cognitive partnership capable of preventing avoidable regret in high-stakes decisions, addressing return-on-investment expectations that depend on AI systems supporting consequential decision-making without introducing preventable cognitive traps when verification arrives too late.

Knowledge Graphs (KGs) serve as a critical foundation for AI systems, yet their automated construction inevitably introduces noise, compromising data trustworthiness. Existing triple verification methods, based on graph embeddings or language models, often suffer from single-source bias by relying on either internal structural constraints or external semantic evidence, and usually follow a static inference paradigm. As a result, they struggle with complex or long-tail facts and provide limited interpretability. To address these limitations, we propose SHARP (Schema-Hybrid Agent for Reliable Prediction), a training-free autonomous agent that reformulates triple verification as a dynamic process of strategic planning, active investigation, and evidential reasoning. Specifically, SHARP combines a Memory-Augmented Mechanism with Schema-Aware Strategic Planning to improve reasoning stability, and employs an enhanced ReAct loop with a Hybrid Knowledge Toolset to dynamically integrate internal KG structure and external textual evidence for cross-verification. Experiments on FB15K-237 and Wikidata5M-Ind show that SHARP significantly outperforms existing state-of-the-art baselines, achieving accuracy gains of 4.2% and 12.9%, respectively. Moreover, SHARP provides transparent, fact-based evidence chains for each judgment, demonstrating strong interpretability and robustness for complex verification tasks.

Having reliable specifications is an unavoidable challenge in achieving verifiable correctness, robustness, and interpretability of AI systems. Existing specifications for neural networks are in the paradigm of data as specification. That is, the local neighborhood centering around a reference input is considered to be correct (or robust). While existing specifications contribute to verifying adversarial robustness, a significant problem in many research domains, our empirical study shows that those verified regions are somewhat tight, and thus fail to allow verification of test set inputs, making them impractical for some real-world applications. To this end, we propose a new family of specifications called neural representation as specification, which uses the intrinsic information of neural networks - neural activation patterns (NAPs), rather than input data to specify the correctness and/or robustness of neural network predictions. We present a simple statistical approach to mining neural activation patterns. To show the effectiveness of discovered NAPs, we formally verify several important properties, such as various types of misclassifications will never happen for a given NAP, and there is no ambiguity between different NAPs. We show that by using NAP, we can verify a significant region of the input space, while still recalling 84% of the data on MNIST. Moreover, we can push the verifiable bound to 10 times larger on the CIFAR10 benchmark. Thus, we argue that NAPs can potentially be used as a more reliable and extensible specification for neural network verification.

Reliable clinical decision support requires medical AI agents capable of safe, multi-step reasoning over structured electronic health records (EHRs). While large language models (LLMs) show promise in healthcare, existing benchmarks inadequately assess performance on action-based tasks involving threshold evaluation, temporal aggregation, and conditional logic. We introduce ART, an Action-based Reasoning clinical Task benchmark for medical AI agents, which mines real-world EHR data to create challenging tasks targeting known reasoning weaknesses. Through analysis of existing benchmarks, we identify three dominant error categories: retrieval failures, aggregation errors, and conditional logic misjudgments. Our four-stage pipeline -- scenario identification, task generation, quality audit, and evaluation -- produces diverse, clinically validated tasks grounded in real patient data. Evaluating GPT-4o-mini and Claude 3.5 Sonnet on 600 tasks shows near-perfect retrieval after prompt refinement, but substantial gaps in aggregation (28--64%) and threshold reasoning (32--38%). By exposing failure modes in action-oriented EHR reasoning, ART advances toward more reliable clinical agents, an essential step for AI systems that reduce cognitive load and administrative burden, supporting workforce capacity in high-demand care settings

Recent progress in multimodal large language models (MLLMs) has demonstrated promising performance on medical benchmarks and in preliminary trials as clinical assistants. Yet, our pilot audit of diagnostic cases uncovers a critical failure mode: instability in early evidence interpretation precedes hallucination, creating branching reasoning trajectories that cascade into globally inconsistent conclusions. This highlights the need for clinical reasoning agents that constrain stochasticity and hallucination while producing auditable decision flows. We introduce MedMMV, a controllable multimodal multi-agent framework for reliable and verifiable clinical reasoning. MedMMV stabilizes reasoning through diversified short rollouts, grounds intermediate steps in a structured evidence graph under the supervision of a Hallucination Detector, and aggregates candidate paths with a Combined Uncertainty scorer. On six medical benchmarks, MedMMV improves accuracy by up to 12.7% and, more critically, demonstrates superior reliability. Blind physician evaluations confirm that MedMMV substantially increases reasoning truthfulness without sacrificing informational content. By controlling instability through a verifiable, multi-agent process, our framework provides a robust path toward deploying trustworthy AI systems in high-stakes domains like clinical decision support.

We demonstrate that LLMs may learn indicators of document usefulness and modulate their updates accordingly. We introduce random strings ("tags") as indicators of usefulness in a synthetic fine-tuning dataset. Fine-tuning on this dataset leads to implicit meta-learning (IML): in further fine-tuning, the model updates to make more use of text that is tagged as useful. We perform a thorough empirical investigation of this phenomenon, finding (among other things) that (i) it occurs in both pretrained LLMs and those trained from scratch, as well as on a vision task, and (ii) larger models and smaller batch sizes tend to give more IML. We also use probing to examine how IML changes the way models store knowledge in their parameters. Finally, we reflect on what our results might imply about capabilities, risks, and controllability of future AI systems. Our code can be found at https://github.com/krasheninnikov/internalization.

Environmental, Social, and Governance (ESG) reports are essential for evaluating sustainability practices, ensuring regulatory compliance, and promoting financial transparency. However, these documents are often lengthy, structurally diverse, and multimodal, comprising dense text, structured tables, complex figures, and layout-dependent semantics. Existing AI systems often struggle to perform reliable document-level reasoning in such settings, and no dedicated benchmark currently exists in ESG domain. To fill the gap, we introduce MMESGBench, a first-of-its-kind benchmark dataset targeted to evaluate multimodal understanding and complex reasoning across structurally diverse and multi-source ESG documents. This dataset is constructed via a human-AI collaborative, multi-stage pipeline. First, a multimodal LLM generates candidate question-answer (QA) pairs by jointly interpreting rich textual, tabular, and visual information from layout-aware document pages. Second, an LLM verifies the semantic accuracy, completeness, and reasoning complexity of each QA pair. This automated process is followed by an expert-in-the-loop validation, where domain specialists validate and calibrate QA pairs to ensure quality, relevance, and diversity. MMESGBench comprises 933 validated QA pairs derived from 45 ESG documents, spanning across seven distinct document types and three major ESG source categories. Questions are categorized as single-page, cross-page, or unanswerable, with each accompanied by fine-grained multimodal evidence. Initial experiments validate that multimodal and retrieval-augmented models substantially outperform text-only baselines, particularly on visually grounded and cross-page tasks. MMESGBench is publicly available as an open-source dataset at https://github.com/Zhanglei1103/MMESGBench.

Earth Observation (EO) provides critical planetary data for environmental monitoring, disaster management, climate science, and other scientific domains. Here we ask: Are AI systems ready for reliable Earth Observation? We introduce \datasetnamenospace, a benchmark of 140 yes/no questions from NASA Earth Observatory articles across 13 topics and 17 satellite sensors. Using Google Earth Engine API as a tool, LLM agents can only achieve an accuracy of 33% because the code fails to run over 58% of the time. We improve the failure rate for open models by fine-tuning synthetic data, allowing much smaller models (Llama-3.1-8B) to achieve comparable accuracy to much larger ones (e.g., DeepSeek-R1). Taken together, our findings identify significant challenges to be solved before AI agents can automate earth observation, and suggest paths forward. The project page is available at https://iandrover.github.io/UnivEarth.

Reliable verification of proofs remains a bottleneck for training and evaluating AI systems on hard mathematical reasoning. Fully formal proofs, in languages like Lean, are easy to verify because they are unambiguous and modular. Most proofs, particularly those written by AI systems, have neither property, and translating them into formal languages remains challenging in many frontier math settings. We propose Pseudo-Formalization (PF), a proof format that captures the modularity and precision of formal proofs while retaining the flexibility of natural language. A Pseudo-Formal proof is decomposed into self-contained modules, each stating its premises, conclusion, and proof in natural language. To verify the correctness of a regular natural language proof, an LLM translates it to Pseudo-Formal and then verifies each module independently, an algorithm we call Block Verification (BV). We evaluate PF+BV on two benchmarks spanning olympiad and research-level mathematics, where it pareto-dominates LLM-as-judge baselines on error-finding precision and recall. To support future work, we release our research-level proof verification benchmark ArxivMathGradingBench.

The paradigm of agentic science requires AI systems to conduct robust reasoning and engage in long-horizon, autonomous exploration. However, current scientific benchmarks remain confined to domain knowledge comprehension and complex reasoning, failing to evaluate the exploratory nature and procedural complexity of real-world research. In this work, we present research-oriented evaluations in theoretical and computational physics, a natural testbed with comprehensive domain knowledge, complex reasoning, and verifiable end-to-end workflows without reliance on experiments. Here we introduce PRL-Bench (Physics Research by LLMs), a benchmark designed to systematically map the capability boundaries of LLMs in executing end-to-end physics research. Constructed from 100 curated papers from the latest issues of Physical Review Letters since August 2025 and validated by domain experts, PRL-Bench covers five major theory- and computation-intensive subfields of modern physics: astrophysics, condensed matter physics, high-energy physics, quantum information, and statistical physics. Each task in the benchmark is designed to replicate the core properties of authentic scientific research, including exploration-oriented formulation, long-horizon workflows, and objective verifiability, thereby reconstructing the essential reasoning processes and research workflows of real physics research. Evaluation across frontier models shows that performance remains limited, with the best overall score below 50, revealing a pronounced gap between current LLM capabilities and the demands of real scientific research. PRL-Bench serves a reliable testbed for accessing next generation AI scientists advancing AI systems toward autonomous scientific discovery.

The rapid deployment of AI systems in high-stakes domains, including those classified as high-risk under the The EU AI Act (Regulation (EU) 2024/1689), has intensified the need for reliable compliance auditing. For binary classifiers, regulatory risk assessment often relies on global fairness metrics such as the Disparate Impact ratio, widely used to evaluate potential discrimination. In typical auditing settings, the auditee provides a subset of its dataset to an auditor, while a supervisory authority may verify whether this subset is representative of the full underlying distribution. In this work, we investigate to what extent a malicious auditee can construct a fairness-compliant yet representative-looking sample from a non-compliant original distribution, thereby creating an illusion of fairness. We formalize this problem as a constrained distributional projection task and introduce mathematically grounded manipulation strategies based on entropic and optimal transport projections. These constructions characterize the minimal distributional shift required to satisfy fairness constraints. To counter such attacks, we formalize representativeness through distributional distance based statistical tests and systematically evaluate their ability to detect manipulated samples. Our analysis highlights the conditions under which fairness manipulation can remain statistically undetected and provides practical guidelines for strengthening supervisory verification. We validate our theoretical findings through experiments on standard tabular datasets for bias detection. Code is publicly available at https://github.com/ValentinLafargue/Inspection.

As the issue of robustness in AI systems becomes vital, statistical learning techniques that are reliable even in presence of partly contaminated data have to be developed. Preference data, in the form of (complete) rankings in the simplest situations, are no exception and the demand for appropriate concepts and tools is all the more pressing given that technologies fed by or producing this type of data (e.g. search engines, recommending systems) are now massively deployed. However, the lack of vector space structure for the set of rankings (i.e. the symmetric group S_n) and the complex nature of statistics considered in ranking data analysis make the formulation of robustness objectives in this domain challenging. In this paper, we introduce notions of robustness, together with dedicated statistical methods, for Consensus Ranking the flagship problem in ranking data analysis, aiming at summarizing a probability distribution on S_n by a median ranking. Precisely, we propose specific extensions of the popular concept of breakdown point, tailored to consensus ranking, and address the related computational issues. Beyond the theoretical contributions, the relevance of the approach proposed is supported by an experimental study.

As large language models (LLMs) advance, the ultimate vision for their role in science is emerging: we could build an AI collaborator to effectively assist human beings throughout the entire scientific research process. We refer to this envisioned system as ResearchGPT. Given that scientific research progresses through multiple interdependent phases, achieving this vision requires rigorous benchmarks that evaluate the end-to-end workflow rather than isolated sub-tasks. To this end, we contribute CS-54k, a high-quality corpus of scientific Q&A pairs in computer science, built from 14k CC-licensed papers. It is constructed through a scalable, paper-grounded pipeline that combines retrieval-augmented generation (RAG) with multi-stage quality control to ensure factual grounding. From this unified corpus, we derive two complementary subsets: CS-4k, a carefully curated benchmark for evaluating AI's ability to assist scientific research, and CS-50k, a large-scale training dataset. Extensive experiments demonstrate that CS-4k stratifies state-of-the-art LLMs into distinct capability tiers. Open models trained on CS-50k with supervised training and reinforcement learning demonstrate substantial improvements. Even 7B-scale models, when properly trained, outperform many larger proprietary systems, such as GPT-4.1, GPT-4o, and Gemini 2.5 Pro. This indicates that making AI models better research assistants relies more on domain-aligned training with high-quality data than on pretraining scale or general benchmark performance. We release CS-4k and CS-50k in the hope of fostering AI systems as reliable collaborators in CS research.

We present app.build (https://github.com/appdotbuild/agent/), an open-source framework that improves LLM-based application generation through systematic validation and structured environments. Our approach combines multi-layered validation pipelines, stack-specific orchestration, and model-agnostic architecture, implemented across three reference stacks. Through evaluation on 30 generation tasks, we demonstrate that comprehensive validation achieves 73.3% viability rate with 30% reaching perfect quality scores, while open-weights models achieve 80.8% of closed-model performance when provided structured environments. The open-source framework has been adopted by the community, with over 3,000 applications generated to date. This work demonstrates that scaling reliable AI agents requires scaling environments, not just models -- providing empirical insights and complete reference implementations for production-oriented agent systems.

To achieve reliable, robust, and safe AI systems, it is vital to implement fallback strategies when AI predictions cannot be trusted. Certifiers for neural networks are a reliable way to check the robustness of these predictions. They guarantee for some predictions that a certain class of manipulations or attacks could not have changed the outcome. For the remaining predictions without guarantees, the method abstains from making a prediction, and a fallback strategy needs to be invoked, which typically incurs additional costs, can require a human operator, or even fail to provide any prediction. While this is a key concept towards safe and secure AI, we show for the first time that this approach comes with its own security risks, as such fallback strategies can be deliberately triggered by an adversary. In addition to naturally occurring abstains for some inputs and perturbations, the adversary can use training-time attacks to deliberately trigger the fallback with high probability. This transfers the main system load onto the fallback, reducing the overall system's integrity and/or availability. We design two novel availability attacks, which show the practical relevance of these threats. For example, adding 1% poisoned data during training is sufficient to trigger the fallback and hence make the model unavailable for up to 100% of all inputs by inserting the trigger. Our extensive experiments across multiple datasets, model architectures, and certifiers demonstrate the broad applicability of these attacks. An initial investigation into potential defenses shows that current approaches are insufficient to mitigate the issue, highlighting the need for new, specific solutions.

As large language models (LLMs) are increasingly integrated into multi-agent and human-AI systems, understanding their awareness of both self-context and conversational partners is essential for ensuring reliable performance and robust safety. While prior work has extensively studied situational awareness which refers to an LLM's ability to recognize its operating phase and constraints, it has largely overlooked the complementary capacity to identify and adapt to the identity and characteristics of a dialogue partner. In this paper, we formalize this latter capability as interlocutor awareness and present the first systematic evaluation of its emergence in contemporary LLMs. We examine interlocutor inference across three dimensions-reasoning patterns, linguistic style, and alignment preferences-and show that LLMs reliably identify same-family peers and certain prominent model families, such as GPT and Claude. To demonstrate its practical significance, we develop three case studies in which interlocutor awareness both enhances multi-LLM collaboration through prompt adaptation and introduces new alignment and safety vulnerabilities, including reward-hacking behaviors and increased jailbreak susceptibility. Our findings highlight the dual promise and peril of identity-sensitive behavior in LLMs, underscoring the need for further understanding of interlocutor awareness and new safeguards in multi-agent deployments. Our code is open-sourced at https://github.com/younwoochoi/InterlocutorAwarenessLLM.

Large language models increasingly serve as conversational agents that adopt personas and role-play characters at user request. This capability, while valuable, raises concerns about sycophancy: the tendency to provide responses that validate users rather than prioritize factual accuracy. While prior work has established that sycophancy poses risks to AI safety and alignment, the relationship between specific personality traits of adopted personas and the degree of sycophantic behavior remains unexplored. We present a systematic investigation of how persona agreeableness influences sycophancy across 13 small, open-weight language models ranging from 0.6B to 20B parameters. We develop a benchmark comprising 275 personas evaluated on NEO-IPIP agreeableness subscales and expose each persona to 4,950 sycophancy-eliciting prompts spanning 33 topic categories. Our analysis reveals that 9 of 13 models exhibit statistically significant positive correlations between persona agreeableness and sycophancy rates, with Pearson correlations reaching r = 0.87 and effect sizes as large as Cohen's d = 2.33. These findings demonstrate that agreeableness functions as a reliable predictor of persona-induced sycophancy, with direct implications for the deployment of role-playing AI systems and the development of alignment strategies that account for personality-mediated deceptive behaviors.

Large vision-language models (VLMs) still struggle with reliable 3D spatial reasoning, a core capability for embodied and physical AI systems. This limitation arises from their inability to capture fine-grained 3D geometry and spatial relationships. While recent efforts have introduced multi-view geometry transformers into VLMs, they typically fuse only the deep-layer features from vision and geometry encoders, discarding rich hierarchical signals and creating a fundamental bottleneck for spatial understanding. To overcome this, we propose SpatialStack, a general hierarchical fusion framework that progressively aligns vision, geometry, and language representations across the model hierarchy. Moving beyond conventional late-stage vision-geometry fusion, SpatialStack stacks and synchronizes multi-level geometric features with the language backbone, enabling the model to capture both local geometric precision and global contextual semantics. Building upon this framework, we develop VLM-SpatialStack, a model that achieves state-of-the-art performance on multiple 3D spatial reasoning benchmarks. Extensive experiments and ablations demonstrate that our multi-level fusion strategy consistently enhances 3D understanding and generalizes robustly across diverse spatial reasoning tasks, establishing SpatialStack as an effective and extensible design paradigm for vision-language-geometry integration in next-generation multimodal physical AI systems.

Large language models (LLMs) are powerful AI tools that can generate and comprehend natural language text and other complex information. However, the field lacks a mathematical framework to systematically describe, compare and improve LLMs. We propose Hex a framework that clarifies key terms and concepts in LLM research, such as hallucinations, alignment, self-verification and chain-of-thought reasoning. The Hex framework offers a precise and consistent way to characterize LLMs, identify their strengths and weaknesses, and integrate new findings. Using Hex, we differentiate chain-of-thought reasoning from chain-of-thought prompting and establish the conditions under which they are equivalent. This distinction clarifies the basic assumptions behind chain-of-thought prompting and its implications for methods that use it, such as self-verification and prompt programming. Our goal is to provide a formal framework for LLMs that can help both researchers and practitioners explore new possibilities for generative AI. We do not claim to have a definitive solution, but rather a tool for opening up new research avenues. We argue that our formal definitions and results are crucial for advancing the discussion on how to build generative AI systems that are safe, reliable, fair and robust, especially in domains like healthcare and software engineering.

Large language models (LLMs) excel at many natural language tasks, yet their reasoning reliability under structured perturbations of rule-based systems remains brittle. We present a controlled evaluation framework consisting of four stress tests: (1) rule deletion (redundant vs. essential), (2) contradictory evidence injection, (3) logic-preserving rewrites, and (4) multi-law equivalence stacking. While representative model families (BERT, Qwen2, and TinyLlama) achieve Acc = 1.0000 on base tasks, our framework reveals a critical failure mode termed Logic Inertia - a total breakdown with Acc = 0.0000 under contradictions, where deductive momentum overrides factual reality. To address this, we propose Conflict-Aware Fusion (Fusion-Conflict), a framework grounded in the Cognitive Structure Hypothesis, which posits that robust reasoning requires an explicit structural inductive bias. By imposing a dual-process architecture that separates premise verification from logical deduction, Conflict-Aware Fusion effectively mitigates logic inertia under the proposed evaluation framework, achieving 1.0000 accuracy on both base and contradictory stress tests. It also significantly enhances robustness to missing evidence. Our results demonstrate that, for reliable multi-step reasoning, structural verification discipline is as critical as training data scale, providing a potential blueprint for building robust, contradiction-aware AI systems this https://github.com/14H034160212/lemo . See the OpenAI/Evals pull request this https://github.com/openai/evals/pull/1622 .

Retrieval-augmented learning based on radiology reports has emerged as a promising direction to improve performance on long-tail medical imaging tasks, such as rare disease detection in chest X-rays. Most existing methods rely on comparing high-dimensional text embeddings from models like CLIP or CXR-BERT, which are often difficult to interpret, computationally expensive, and not well-aligned with the structured nature of medical knowledge. We propose a novel, ontology-driven alternative for comparing radiology report texts based on clinically grounded concepts from the Unified Medical Language System (UMLS). Our method extracts standardised medical entities from free-text reports using an enhanced pipeline built on RadGraph-XL and SapBERT. These entities are linked to UMLS concepts (CUIs), enabling a transparent, interpretable set-based representation of each report. We then define a task-adaptive similarity measure based on a modified and weighted version of the Tversky Index that accounts for synonymy, negation, and hierarchical relationships between medical entities. This allows efficient and semantically meaningful similarity comparisons between reports. We demonstrate that our approach outperforms state-of-the-art embedding-based retrieval methods in a radiograph classification task on MIMIC-CXR, particularly in long-tail settings. Additionally, we use our pipeline to generate ontology-backed disease labels for MIMIC-CXR, offering a valuable new resource for downstream learning tasks. Our work provides more explainable, reliable, and task-specific retrieval strategies in clinical AI systems, especially when interpretability and domain knowledge integration are essential. Our code is available at https://github.com/Felix-012/ontology-concept-distillation

The Model Context Protocol (MCP) is rapidly emerging as a pivotal open standard, designed to enhance agent-tool integration and interoperability, and is positioned to unlock a new era of powerful, interconnected, and genuinely utilitarian agentic AI. However, despite MCP's growing adoption, existing benchmarks often fail to capture real-world agent performance within this new paradigm, leading to a distorted perception of their true operational value and an inability to reliably differentiate proficiencies. To bridge this critical evaluation gap, we introduce MCP-AgentBench -- a comprehensive benchmark specifically engineered to rigorously assess language agent capabilities in MCP-mediated tool interactions. Core contributions of MCP-AgentBench include: the establishment of a robust MCP testbed comprising 33 operational servers with 188 distinct tools; the development of a benchmark featuring 600 systematically designed queries distributed across 6 distinct categories of varying interaction complexity; and the introduction of MCP-Eval, a novel outcome-oriented evaluation methodology prioritizing real-world task success. Through extensive empirical evaluation of leading language agents, we provide foundational insights. MCP-AgentBench aims to equip the research community with a standardized and reliable framework to build, validate, and advance agents capable of fully leveraging MCP's transformative benefits, thereby accelerating progress toward truly capable and interoperable AI systems.

Large Language Models (LLMs) are predominantly governed by probabilistic frameworks in which the sum of outcome probabilities is constrained to unity. This architectural limitation, often imposed by Softmax layers, leads to a collapse of uncertainty that makes it difficult to differentiate between epistemic uncertainty, paradox, and vagueness. We present an empirical investigation of the application of Neutrosophic Logic, a framework that treats Truth (T), Indeterminacy (I), and Falsity (F) as three independent dimensions, to model epistemic states in LLMs. We conducted experiments on a family of four OpenAI GPT models across five linguistic phenomena: logical paradoxes, epistemic ignorance, vagueness, ethical contradictions, and future contingencies, under three prompting strategies: neutrosophic, probabilistic, and entropy-derived. Our findings reveal that the neutrosophic approach, by allowing T+I+F > 1, a state we term hyper-truth, provides a richer representation of a model's internal state. In 35% of evaluations, hyper-truth emerged spontaneously, predominantly under ethical contradiction and logical paradox. We demonstrate that this approach preserves truth values in fuzzy contexts and offers a robust method for identifying and quantifying internal model conflict. We conclude that the integration of neutrosophic evaluation layers is a critical step toward more transparent, reliable, and ethically aware AI systems.

Language models exhibit remarkable natural language generation capabilities but remain prone to hallucinations, generating factually incorrect information despite producing syntactically coherent responses. This study introduces the Licensing Oracle, an architectural solution designed to stem hallucinations in LMs by enforcing truth constraints through formal validation against structured knowledge graphs. Unlike statistical approaches that rely on data scaling or fine-tuning, the Licensing Oracle embeds a deterministic validation step into the model's generative process, ensuring that only factually accurate claims are made. We evaluated the effectiveness of the Licensing Oracle through experiments comparing it with several state-of-the-art methods, including baseline language model generation, fine-tuning for factual recall, fine-tuning for abstention behavior, and retrieval-augmented generation (RAG). Our results demonstrate that although RAG and fine-tuning improve performance, they fail to eliminate hallucinations. In contrast, the Licensing Oracle achieved perfect abstention precision (AP = 1.0) and zero false answers (FAR-NE = 0.0), ensuring that only valid claims were generated with 89.1% accuracy in factual responses. This work shows that architectural innovations, such as the Licensing Oracle, offer a necessary and sufficient solution for hallucinations in domains with structured knowledge representations, offering guarantees that statistical methods cannot match. Although the Licensing Oracle is specifically designed to address hallucinations in fact-based domains, its framework lays the groundwork for truth-constrained generation in future AI systems, providing a new path toward reliable, epistemically grounded models.

Medical Visual Question Answering (MedVQA) is a promising field for developing clinical decision support systems, yet progress is often limited by the available datasets, which can lack clinical complexity and visual diversity. To address these gaps, we introduce Kvasir-VQA-x1, a new, large-scale dataset for gastrointestinal (GI) endoscopy. Our work significantly expands upon the original Kvasir-VQA by incorporating 159,549 new question-answer pairs that are designed to test deeper clinical reasoning. We developed a systematic method using large language models to generate these questions, which are stratified by complexity to better assess a model's inference capabilities. To ensure our dataset prepares models for real-world clinical scenarios, we have also introduced a variety of visual augmentations that mimic common imaging artifacts. The dataset is structured to support two main evaluation tracks: one for standard VQA performance and another to test model robustness against these visual perturbations. By providing a more challenging and clinically relevant benchmark, Kvasir-VQA-x1 aims to accelerate the development of more reliable and effective multimodal AI systems for use in clinical settings. The dataset is fully accessible and adheres to FAIR data principles, making it a valuable resource for the wider research community. Code and data: https://github.com/Simula/Kvasir-VQA-x1 and https://huggingface.co/datasets/SimulaMet/Kvasir-VQA-x1

Chain-of-Thought (CoT) reasoning has proven effective in enhancing large language models by encouraging step-by-step intermediate reasoning, and recent advances have extended this paradigm to Multimodal Large Language Models (MLLMs). In the medical domain, where diagnostic decisions depend on nuanced visual cues and sequential reasoning, CoT aligns naturally with clinical thinking processes. However, Current benchmarks for medical image understanding generally focus on the final answer while ignoring the reasoning path. An opaque process lacks reliable bases for judgment, making it difficult to assist doctors in diagnosis. To address this gap, we introduce a new M3CoTBench benchmark specifically designed to evaluate the correctness, efficiency, impact, and consistency of CoT reasoning in medical image understanding. M3CoTBench features 1) a diverse, multi-level difficulty dataset covering 24 examination types, 2) 13 varying-difficulty tasks, 3) a suite of CoT-specific evaluation metrics (correctness, efficiency, impact, and consistency) tailored to clinical reasoning, and 4) a performance analysis of multiple MLLMs. M3CoTBench systematically evaluates CoT reasoning across diverse medical imaging tasks, revealing current limitations of MLLMs in generating reliable and clinically interpretable reasoning, and aims to foster the development of transparent, trustworthy, and diagnostically accurate AI systems for healthcare. Project page at https://juntaojianggavin.github.io/projects/M3CoTBench/.

Traditional evaluations of multimodal large language models (LLMs) have been limited by their focus on single-image reasoning, failing to assess crucial aspects like contextual understanding, reasoning stability, and uncertainty calibration. This study addresses these limitations by introducing a novel benchmark that integrates multi-image reasoning tasks with rejection-based evaluation and positional bias detection. To evaluate these dimensions, we further introduce entropy as a novel metric for quantifying reasoning consistency across reordered answer variants. We applied this benchmark to assess Grok 3, ChatGPT-4o, ChatGPT-o1, Gemini 2.0 Flash Experimental, DeepSeek Janus models, Qwen2.5-VL-72B-Instruct, QVQ-72B-Preview, and Pixtral 12B across eight visual reasoning tasks, including difference spotting and diagram interpretation. Our findings reveal ChatGPT-o1 leading in overall accuracy (82.5\%) and rejection accuracy (70.0\%), closely followed by Gemini 2.0 Flash Experimental (70.8\%). QVQ-72B-Preview demonstrated superior rejection accuracy (85.5\%). Notably, Pixtral 12B (51.7\%) showed promise in specific domains, while Janus models exhibited challenges in bias and uncertainty calibration, reflected in low rejection accuracies and high entropy scores. High entropy scores in Janus models (Janus 7B: 0.8392, Janus 1B: 0.787) underscore their susceptibility to positional bias and unstable reasoning, contrasting with the low entropy and robust reasoning of ChatGPT models. The study further demonstrates that model size is not the sole determinant of performance, as evidenced by Grok 3 underperformance despite its substantial parameter count. By employing multi-image contexts, rejection mechanisms, and entropy-based consistency metrics, this benchmark sets a new standard for evaluating multimodal LLMs, enabling a more robust and reliable assessment of next-generation AI systems.

Traditional software relies on contracts -- APIs, type systems, assertions -- to specify and enforce correct behavior. AI agents, by contrast, operate on prompts and natural language instructions with no formal behavioral specification. This gap is the root cause of drift, governance failures, and frequent project failures in agentic AI deployments. We introduce Agent Behavioral Contracts (ABC), a formal framework that brings Design-by-Contract principles to autonomous AI agents. An ABC contract C = (P, I, G, R) specifies Preconditions, Invariants, Governance policies, and Recovery mechanisms as first-class, runtime-enforceable components. We define (p, delta, k)-satisfaction -- a probabilistic notion of contract compliance that accounts for LLM non-determinism and recovery -- and prove a Drift Bounds Theorem showing that contracts with recovery rate gamma > alpha (the natural drift rate) bound behavioral drift to D* = alpha/gamma in expectation, with Gaussian concentration in the stochastic setting. We establish sufficient conditions for safe contract composition in multi-agent chains and derive probabilistic degradation bounds. We implement ABC in AgentAssert, a runtime enforcement library, and evaluate on AgentContract-Bench, a benchmark of 200 scenarios across 7 models from 6 vendors. Results across 1,980 sessions show that contracted agents detect 5.2-6.8 soft violations per session that uncontracted baselines miss entirely (p < 0.0001, Cohen's d = 6.7-33.8), achieve 88-100% hard constraint compliance, and bound behavioral drift to D* < 0.27 across extended sessions, with 100% recovery for frontier models and 17-100% across all models, at overhead < 10 ms per action.

Claude Code is an agentic coding tool that can run shell commands, edit files, and call external services on behalf of the user. This study describes its comprehensive architecture by analyzing the publicly available TypeScript source code and further comparing it with OpenClaw, an independent open-source AI agent system that answers many of the same design questions from a different deployment context. Our analysis identifies five human values, philosophies, and needs that motivate the architecture (human decision authority, safety and security, reliable execution, capability amplification, and contextual adaptability) and traces them through thirteen design principles to specific implementation choices. The core of the system is a simple while-loop that calls the model, runs tools, and repeats. Most of the code, however, lives in the systems around this loop: a permission system with seven modes and an ML-based classifier, a five-layer compaction pipeline for context management, four extensibility mechanisms (MCP, plugins, skills, and hooks), a subagent delegation mechanism with worktree isolation, and append-oriented session storage. A comparison with OpenClaw, a multi-channel personal assistant gateway, shows that the same recurring design questions produce different architectural answers when the deployment context changes: from per-action safety classification to perimeter-level access control, from a single CLI loop to an embedded runtime within a gateway control plane, and from context-window extensions to gateway-wide capability registration. We finally identify six open design directions for future agent systems, grounded in recent empirical, architectural, and policy literature.

Current benchmarks for AI clinician systems, often based on multiple-choice exams or manual rubrics, fail to capture the depth, robustness, and safety required for real-world clinical practice. To address this, we introduce the GAPS framework, a multidimensional paradigm for evaluating Grounding (cognitive depth), Adequacy (answer completeness), Perturbation (robustness), and Safety. Critically, we developed a fully automated, guideline-anchored pipeline to construct a GAPS-aligned benchmark end-to-end, overcoming the scalability and subjectivity limitations of prior work. Our pipeline assembles an evidence neighborhood, creates dual graph and tree representations, and automatically generates questions across G-levels. Rubrics are synthesized by a DeepResearch agent that mimics GRADE-consistent, PICO-driven evidence review in a ReAct loop. Scoring is performed by an ensemble of large language model (LLM) judges. Validation confirmed our automated questions are high-quality and align with clinician judgment. Evaluating state-of-the-art models on the benchmark revealed key failure modes: performance degrades sharply with increased reasoning depth (G-axis), models struggle with answer completeness (A-axis), and they are highly vulnerable to adversarial perturbations (P-axis) as well as certain safety issues (S-axis). This automated, clinically-grounded approach provides a reproducible and scalable method for rigorously evaluating AI clinician systems and guiding their development toward safer, more reliable clinical practice.

Artificial Intelligence (AI) is starting to transform the research process as we know it by automating the discovery of new solutions. Given a task, the typical AI-driven approach is (i) to generate a set of diverse solutions, and then (ii) to verify these solutions and select one that solves the problem. Crucially, this approach assumes the existence of a reliable verifier, i.e., one that can accurately determine whether a solution solves the given problem. We argue that systems research, long focused on designing and evaluating new performance-oriented algorithms, is particularly well-suited for AI-driven solution discovery. This is because system performance problems naturally admit reliable verifiers: solutions are typically implemented in real systems or simulators, and verification reduces to running these software artifacts against predefined workloads and measuring performance. We term this approach as AI-Driven Research for Systems (ADRS), which iteratively generates, evaluates, and refines solutions. Using penEvolve, an existing open-source ADRS instance, we present case studies across diverse domains, including load balancing for multi-region cloud scheduling, Mixture-of-Experts inference, LLM-based SQL queries, and transaction scheduling. In multiple instances, ADRS discovers algorithms that outperform state-of-the-art human designs (e.g., achieving up to 5.0x runtime improvements or 50% cost reductions). We distill best practices for guiding algorithm evolution, from prompt design to evaluator construction, for existing frameworks. We then discuss the broader implications for the systems community: as AI assumes a central role in algorithm design, we argue that human researchers will increasingly focus on problem formulation and strategic guidance. Our results highlight both the disruptive potential and the urgent need to adapt systems research practices in the age of AI.

The rapid advancement of large language models (LLMs) has enabled new possibilities for applying artificial intelligence within the legal domain. Nonetheless, the complexity, hierarchical organization, and frequent revisions of Vietnamese legislation pose considerable challenges for evaluating how well these models interpret and utilize legal knowledge. To address this gap, the Vietnamese Legal Benchmark (VLegal-Bench) is introduced, the first comprehensive benchmark designed to systematically assess LLMs on Vietnamese legal tasks. Informed by Bloom's cognitive taxonomy, VLegal-Bench encompasses multiple levels of legal understanding through tasks designed to reflect practical usage scenarios. The benchmark comprises 10,450 samples generated through a rigorous annotation pipeline, where legal experts label and cross-validate each instance using our annotation system to ensure every sample is grounded in authoritative legal documents and mirrors real-world legal assistant workflows, including general legal questions and answers, retrieval-augmented generation, multi-step reasoning, and scenario-based problem solving tailored to Vietnamese law. By providing a standardized, transparent, and cognitively informed evaluation framework, VLegal-Bench establishes a solid foundation for assessing LLM performance in Vietnamese legal contexts and supports the development of more reliable, interpretable, and ethically aligned AI-assisted legal systems. To facilitate access and reproducibility, we provide a public landing page for this benchmark at https://vilegalbench.cmcai.vn/.

The development of Artificial Intelligence (AI), including AI in Science (AIS), should be done following the principles of responsible AI. Progress in responsible AI is often quantified through evaluation metrics, yet there has been less work on assessing the robustness and reliability of the metrics themselves. We reflect on prior work that examines the robustness of fairness metrics for recommender systems as a type of AI application and summarise their key takeaways into a set of non-exhaustive guidelines for developing reliable metrics of responsible AI. Our guidelines apply to a broad spectrum of AI applications, including AIS.

The rapid advancement of Large Language Models (LLMs) is catalyzing a shift towards autonomous AI Agents capable of executing complex, multi-step tasks. However, these agents remain brittle when faced with real-world exceptions, making Human-in-the-Loop (HITL) supervision essential for mission-critical applications. In this paper, we present AgentBay, a novel sandbox service designed from the ground up for hybrid interaction. AgentBay provides secure, isolated execution environments spanning Windows, Linux, Android, Web Browsers, and Code interpreters. Its core contribution is a unified session accessible via a hybrid control interface: An AI agent can interact programmatically via mainstream interfaces (MCP, Open Source SDK), while a human operator can, at any moment, seamlessly take over full manual control. This seamless intervention is enabled by Adaptive Streaming Protocol (ASP). Unlike traditional VNC/RDP, ASP is specifically engineered for this hybrid use case, delivering an ultra-low-latency, smoother user experience that remains resilient even in weak network environments. It achieves this by dynamically blending command-based and video-based streaming, adapting its encoding strategy based on network conditions and the current controller (AI or human). Our evaluation demonstrates strong results in security, performance, and task completion rates. In a benchmark of complex tasks, the AgentBay (Agent + Human) model achieved more than 48% success rate improvement. Furthermore, our ASP protocol reduces bandwidth consumption by up to 50% compared to standard RDP, and in end-to-end latency with around 5% reduction, especially under poor network conditions. We posit that AgentBay provides a foundational primitive for building the next generation of reliable, human-supervised autonomous systems.

Recent advancements in Large Multimodal Models (LMMs) have significantly improved multimodal understanding and generation. However, these models still struggle to generate tightly interleaved image-text outputs, primarily due to the limited scale, quality and instructional richness of current training datasets. To address this, we introduce InterSyn, a large-scale multimodal dataset constructed using our Self-Evaluation with Iterative Refinement (SEIR) method. InterSyn features multi-turn, instruction-driven dialogues with tightly interleaved imagetext responses, providing rich object diversity and rigorous automated quality refinement, making it well-suited for training next-generation instruction-following LMMs. Furthermore, to address the lack of reliable evaluation tools capable of assessing interleaved multimodal outputs, we introduce SynJudge, an automatic evaluation model designed to quantitatively assess multimodal outputs along four dimensions: text content, image content, image quality, and image-text synergy. Experimental studies show that the SEIR method leads to substantially higher dataset quality compared to an otherwise identical process without refinement. Moreover, LMMs trained on InterSyn achieve uniform performance gains across all evaluation metrics, confirming InterSyn's utility for advancing multimodal systems.

This study investigates the use of generative AI and multi-agent systems to provide automatic feedback in educational contexts, particularly for student constructed responses in science assessments. The research addresses a key gap in the field by exploring how multi-agent systems, called AutoFeedback, can improve the quality of GenAI-generated feedback, overcoming known issues such as over-praise and over-inference that are common in single-agent large language models (LLMs). The study developed a multi-agent system consisting of two AI agents: one for generating feedback and another for validating and refining it. The system was tested on a dataset of 240 student responses, and its performance was compared to that of a single-agent LLM. Results showed that AutoFeedback significantly reduced the occurrence of over-praise and over-inference errors, providing more accurate and pedagogically sound feedback. The findings suggest that multi-agent systems can offer a more reliable solution for generating automated feedback in educational settings, highlighting their potential for scalable and personalized learning support. These results have important implications for educators and researchers seeking to leverage AI in formative assessments, offering a pathway to more effective feedback mechanisms that enhance student learning outcomes.

Users across enterprises increasingly rely on AI agents to query their data through natural language. However, building reliable data agents remains difficult because real-world data is often fragmented across multiple heterogeneous database systems, with inconsistent references and information buried in unstructured text. Existing benchmarks only tackle individual pieces of this problem -- e.g., translating natural-language questions into SQL queries, answering questions over small tables provided in context -- but do not evaluate the full pipeline of integrating, transforming, and analyzing data across multiple database systems. To fill this gap, we present the Data Agent Benchmark (DAB), grounded in a formative study of enterprise data agent workloads across six industries. DAB comprises 54 queries across 12 datasets, 9 domains, and 4 database management systems. On DAB, the best frontier model (Gemini-3-Pro) achieves only 38% pass@1 accuracy. We benchmark five frontier LLMs, analyze their failure modes, and distill takeaways for future data agent development. Our benchmark and experiment code are published at github.com/ucbepic/DataAgentBench.

We introduce [Cosmos-Predict2.5], the latest generation of the Cosmos World Foundation Models for Physical AI. Built on a flow-based architecture, [Cosmos-Predict2.5] unifies Text2World, Image2World, and Video2World generation in a single model and leverages [Cosmos-Reason1], a Physical AI vision-language model, to provide richer text grounding and finer control of world simulation. Trained on 200M curated video clips and refined with reinforcement learning-based post-training, [Cosmos-Predict2.5] achieves substantial improvements over [Cosmos-Predict1] in video quality and instruction alignment, with models released at 2B and 14B scales. These capabilities enable more reliable synthetic data generation, policy evaluation, and closed-loop simulation for robotics and autonomous systems. We further extend the family with [Cosmos-Transfer2.5], a control-net style framework for Sim2Real and Real2Real world translation. Despite being 3.5times smaller than [Cosmos-Transfer1], it delivers higher fidelity and robust long-horizon video generation. Together, these advances establish [Cosmos-Predict2.5] and [Cosmos-Transfer2.5] as versatile tools for scaling embodied intelligence. To accelerate research and deployment in Physical AI, we release source code, pretrained checkpoints, and curated benchmarks under the NVIDIA Open Model License at https://github.com/nvidia-cosmos/cosmos-predict2.5 and https://github.com/nvidia-cosmos/cosmos-transfer2.5. We hope these open resources lower the barrier to adoption and foster innovation in building the next generation of embodied intelligence.

Large language models (LLMs) are increasingly applied in mental health support systems, where reliable recognition of high-risk states such as suicidal ideation and self-harm is safety-critical. However, existing evaluations primarily rely on aggregate performance metrics, which often obscure risk-specific failure modes and provide limited insight into model behavior in realistic, multi-turn interactions. We present MHDash, an open-source platform designed to support the development, evaluation, and auditing of AI systems for mental health applications. MHDash integrates data collection, structured annotation, multi-turn dialogue generation, and baseline evaluation into a unified pipeline. The platform supports annotations across multiple dimensions, including Concern Type, Risk Level, and Dialogue Intent, enabling fine-grained and risk-aware analysis. Our results reveal several key findings: (i) simple baselines and advanced LLM APIs exhibit comparable overall accuracy yet diverge significantly on high-risk cases; (ii) some LLMs maintain consistent ordinal severity ranking while failing absolute risk classification, whereas others achieve reasonable aggregate scores but suffer from high false negative rates on severe categories; and (iii) performance gaps are amplified in multi-turn dialogues, where risk signals emerge gradually. These observations demonstrate that conventional benchmarks are insufficient for safety-critical mental health settings. By releasing MHDash as an open platform, we aim to promote reproducible research, transparent evaluation, and safety-aligned development of AI systems for mental health support.

Retrieval-augmented generation (RAG) systems are increasingly used to analyze complex policy documents, but achieving sufficient reliability for expert usage remains challenging in domains characterized by dense legal language and evolving, overlapping regulatory frameworks. We study the application of RAG to AI governance and policy analysis using the AI Governance and Regulatory Archive (AGORA) corpus, a curated collection of 947 AI policy documents. Our system combines a ColBERT-based retriever fine-tuned with contrastive learning and a generator aligned to human preferences using Direct Preference Optimization (DPO). We construct synthetic queries and collect pairwise preferences to adapt the system to the policy domain. Through experiments evaluating retrieval quality, answer relevance, and faithfulness, we find that domain-specific fine-tuning improves retrieval metrics but does not consistently improve end-to-end question answering performance. In some cases, stronger retrieval counterintuitively leads to more confident hallucinations when relevant documents are absent from the corpus. These results highlight a key concern for those building policy-focused RAG systems: improvements to individual components do not necessarily translate to more reliable answers. Our findings provide practical insights for designing grounded question-answering systems over dynamic regulatory corpora.

Large language models (LLMs) are increasingly being used for complex research tasks such as literature review, idea generation, and scientific paper analysis, yet their ability to truly understand and process the intricate relationships within complex research papers, such as the logical links between claims and supporting evidence remains largely unexplored. In this study, we present CLAIM-BENCH, a comprehensive benchmark for evaluating LLMs' capabilities in scientific claim-evidence extraction and validation, a task that reflects deeper comprehension of scientific argumentation. We systematically compare three approaches which are inspired by divide and conquer approaches, across six diverse LLMs, highlighting model-specific strengths and weaknesses in scientific comprehension. Through evaluation involving over 300 claim-evidence pairs across multiple research domains, we reveal significant limitations in LLMs' ability to process complex scientific content. Our results demonstrate that closed-source models like GPT-4 and Claude consistently outperform open-source counterparts in precision and recall across claim-evidence identification tasks. Furthermore, strategically designed three-pass and one-by-one prompting approaches significantly improve LLMs' abilities to accurately link dispersed evidence with claims, although this comes at increased computational cost. CLAIM-BENCH sets a new standard for evaluating scientific comprehension in LLMs, offering both a diagnostic tool and a path forward for building systems capable of deeper, more reliable reasoning across full-length papers.

The integration of Artificial Intelligence (AI) into clinical settings presents a software engineering challenge, demanding a shift from isolated models to robust, governable, and reliable systems. However, brittle, prototype-derived architectures often plague industrial applications and a lack of systemic oversight, creating a ``responsibility vacuum'' where safety and accountability are compromised. This paper presents an industry case study of the ``Maria'' platform, a production-grade AI system in primary healthcare that addresses this gap. Our central hypothesis is that trustworthy clinical AI is achieved through the holistic integration of four foundational engineering pillars. We present a synergistic architecture that combines Clean Architecture for maintainability with an Event-driven architecture for resilience and auditability. We introduce the Agent as the primary unit of modularity, each possessing its own autonomous MLOps lifecycle. Finally, we show how a Human-in-the-Loop governance model is technically integrated not merely as a safety check, but as a critical, event-driven data source for continuous improvement. We present the platform as a reference architecture, offering practical lessons for engineers building maintainable, scalable, and accountable AI-enabled systems in high-stakes domains.

The rapid proliferation of LLM agent frameworks has forced developers to choose between vendor lock-in through provider-specific SDKs and complex multi-package ecosystems that obscure control flow and hinder reproducibility. Integrating tool calling across multiple LLM providers remains a core engineering challenge due to fragmented APIs, incompatible message formats, and inconsistent streaming and tool-calling behavior, making it difficult to build portable, reliable agent systems. We introduce Orchestral, a lightweight Python framework that provides a unified, type-safe interface for building LLM agents across major providers while preserving the simplicity required for scientific computing and production deployment. Orchestral defines a single universal representation for messages, tools, and LLM usage that operates seamlessly across providers, eliminating manual format translation and reducing framework-induced complexity. Automatic tool schema generation from Python type hints removes the need for handwritten descriptors while maintaining type safety across provider boundaries. A synchronous execution model with streaming support enables deterministic behavior, straightforward debugging, and real-time interaction without introducing server dependencies. The framework's modular architecture cleanly separates provider integration, tool execution, conversation orchestration, and user-facing interfaces, enabling extensibility without architectural entanglement. Orchestral supports advanced agent capabilities found in larger frameworks, including rich tool calling, context compaction, workspace sandboxing, user approval workflows, sub-agents, memory management, and MCP integration.

Artificial Intelligence is moving from models that only generate text to Agentic AI, where systems behave as autonomous entities that can perceive, reason, plan, and act. Large Language Models (LLMs) are no longer used only as passive knowledge engines but as cognitive controllers that combine memory, tool use, and feedback from their environment to pursue extended goals. This shift already supports the automation of complex workflows in software engineering, scientific discovery, and web navigation, yet the variety of emerging designs, from simple single loop agents to hierarchical multi agent systems, makes the landscape hard to navigate. In this paper, we investigate architectures and propose a unified taxonomy that breaks agents into Perception, Brain, Planning, Action, Tool Use, and Collaboration. We use this lens to describe the move from linear reasoning procedures to native inference time reasoning models, and the transition from fixed API calls to open standards like the Model Context Protocol (MCP) and Native Computer Use. We also group the environments in which these agents operate, including digital operating systems, embodied robotics, and other specialized domains, and we review current evaluation practices. Finally, we highlight open challenges, such as hallucination in action, infinite loops, and prompt injection, and outline future research directions toward more robust and reliable autonomous systems.

The rise of OpenClaw in early 2026 marks the moment when millions of users began deploying personal AI agents into their daily lives, delegating tasks ranging from travel planning to multi-step research. This scale of adoption signals that two parallel arcs of development have reached an inflection point. First is a paradigm shift in AI engineering, evolving from prompt and context engineering to harness engineering-designing the complete infrastructure necessary to transform unconstrained agents into controllable, auditable, and production-reliable systems. As model capabilities converge, this harness layer is becoming the primary site of architectural differentiation. Second is the evolution of human-agent interaction from discrete tasks toward a persistent, contextually aware collaborative relationship, which demands open, trustworthy and extensible harness infrastructure. We present SemaClaw, an open-source multi-agent application framework that addresses these shifts by taking a step towards general-purpose personal AI agents through harness engineering. Our primary contributions include a DAG-based two-phase hybrid agent team orchestration method, a PermissionBridge behavioral safety system, a three-tier context management architecture, and an agentic wiki skill for automated personal knowledge base construction.

The rise of Large Language Models (LLMs) necessitates accurate AI-generated text detection. However, current approaches largely overlook the influence of author characteristics. We investigate how sociolinguistic attributes-gender, CEFR proficiency, academic field, and language environment-impact state-of-the-art AI text detectors. Using the ICNALE corpus of human-authored texts and parallel AI-generated texts from diverse LLMs, we conduct a rigorous evaluation employing multi-factor ANOVA and weighted least squares (WLS). Our results reveal significant biases: CEFR proficiency and language environment consistently affected detector accuracy, while gender and academic field showed detector-dependent effects. These findings highlight the crucial need for socially aware AI text detection to avoid unfairly penalizing specific demographic groups. We offer novel empirical evidence, a robust statistical framework, and actionable insights for developing more equitable and reliable detection systems in real-world, out-of-domain contexts. This work paves the way for future research on bias mitigation, inclusive evaluation benchmarks, and socially responsible LLM detectors.

Large Language Models (LLMs) are undergoing a fundamental transformation from conversational generators into integrated AI systems capable of reasoning, action, memory, and self-improvement. We conceptualize this transition as a shift from Chatbot to Digital Colleague: from conversational answers to persistent work. We organize this transition along two tightly coupled dimensions. First, at the cognitive core level, LLMs are advancing from Chatbot-era "fast thinking" systems driven by next-token prediction toward Thinking LLMs that leverage inference-time computation, Chain-of-Thought reasoning, reflection, process supervision, and reinforcement learning to support more deliberate and reliable cognition. Second, at the tool-augmented task execution level, LLMs are progressing from tool-calling Agents that invoke external resources in an ad hoc manner toward OpenClaw-style workstation systems (OpenClaw) equipped with persistent Workspaces, skills, verification loops, and governance. The "Workspace + Skill" paradigm makes episodic tool use colleague-like via state persistence, reusable procedures, task closure, and experience reuse. We examine data construction shifts from instruction-response pairs to State-Action-Observation trajectories and evaluation from static benchmarks to sandboxed, auditable, self-evolving AI ecosystems.

Recent advancements have expanded the role of Large Language Models in board games from playing agents to creative co-designers. However, a critical gap remains: current systems lack the capacity to offer constructive critique grounded in the emergent user experience. Bridging this gap is fundamental for harmonizing Human-AI collaboration, as it empowers designers to refine their creations via external perspectives while steering models away from biased or unpredictable outcomes. Automating critique for board games presents two challenges: inferring the latent dynamics connecting rules to gameplay without an explicit engine, and modeling the subjective heterogeneity of diverse player groups. To address these, we curate a dataset of 1,727 structurally corrected rulebooks and 150K reviews selected via quality scoring and facet-aware sampling. We augment this data with Mechanics-Dynamics-Aesthetics (MDA) reasoning to explicitly bridge the causal gap between written rules and player experience. We further distill player personas and introduce MeepleLM, a specialized model that internalizes persona-specific reasoning patterns to accurately simulate the subjective feedback of diverse player archetypes. Experiments demonstrate that MeepleLM significantly outperforms latest commercial models (e.g., GPT-5.1, Gemini3-Pro) in community alignment and critique quality, achieving a 70% preference rate in user studies assessing utility. MeepleLM serves as a reliable virtual playtester for general interactive systems, marking a pivotal step towards audience-aligned, experience-aware Human-AI collaboration.

AI glasses present a compelling platform for AI agents to serve as personalized memory assistants. To be genuinely useful, such systems must move beyond short-term video comprehension and address memory gaps that humans experience for practical, personal, or social purposes over longitudinal egocentric video streams. However, existing egocentric datasets predominantly focus on action recognition or generic QAs from short clips, measuring perceptual capabilities rather than realistic human memory needs. We introduce SuperMemory-VQA, an egocentric visual question answering (VQA) dataset for evaluating AI assistants on practical, long-horizon memory tasks. It contains 52.9 hours of everyday activities recorded with AI glasses, including synchronized RGB video, audio transcription, eye gaze, IMU, and SLAM trajectories. Through a human-verified annotation pipeline, we construct grounded 4,853 question-answer pairs that span object and location memory, intent recall, visual scene recall, timeline reconstruction, conversational memory, and in-context retrieval. Each question is posed as multiple-choice with an explicit "unanswerable" option to test hallucination robustness. Benchmarking leading agentic frameworks and LLM backbones reveals that existing systems remain far from reliable on real-world memory tasks, highlighting the need for new architectures for grounded AI memory that can answer only when evidence is sufficient. A participant survey further supports that our questions are realistic, useful, and aligned with everyday memory needs.

Artificial intelligence (AI), and especially its sub-field of Machine Learning (ML), are impacting the daily lives of everyone with their ubiquitous applications. In recent years, AI researchers and practitioners have introduced principles and guidelines to build systems that make reliable and trustworthy decisions. From a practical perspective, conventional ML systems process historical data to extract the features that are consequently used to train ML models that perform the desired task. However, in practice, a fundamental challenge arises when the system needs to be operationalized and deployed to evolve and operate in real-life environments continuously. To address this challenge, Machine Learning Operations (MLOps) have emerged as a potential recipe for standardizing ML solutions in deployment. Although MLOps demonstrated great success in streamlining ML processes, thoroughly defining the specifications of robust MLOps approaches remains of great interest to researchers and practitioners. In this paper, we provide a comprehensive overview of the trustworthiness property of MLOps systems. Specifically, we highlight technical practices to achieve robust MLOps systems. In addition, we survey the existing research approaches that address the robustness aspects of ML systems in production. We also review the tools and software available to build MLOps systems and summarize their support to handle the robustness aspects. Finally, we present the open challenges and propose possible future directions and opportunities within this emerging field. The aim of this paper is to provide researchers and practitioners working on practical AI applications with a comprehensive view to adopt robust ML solutions in production environments.

While ongoing advancements in Large Language Models have demonstrated remarkable success across various NLP tasks, Retrieval Augmented Generation Model stands out to be highly effective on downstream applications like Question Answering. Recently, RAG-end2end model further optimized the architecture and achieved notable performance improvements on domain adaptation. However, the effectiveness of these RAG-based architectures remains relatively unexplored when fine-tuned on specialized domains such as customer service for building a reliable conversational AI system. Furthermore, a critical challenge persists in reducing the occurrence of hallucinations while maintaining high domain-specific accuracy. In this paper, we investigated the performance of diverse RAG and RAG-like architectures through domain adaptation and evaluated their ability to generate accurate and relevant response grounded in the contextual knowledge base. To facilitate the evaluation of the models, we constructed a novel dataset HotelConvQA, sourced from wide range of hotel-related conversations and fine-tuned all the models on our domain specific dataset. We also addressed a critical research gap on determining the impact of domain adaptation on reducing hallucinations across different RAG architectures, an aspect that was not properly measured in prior work. Our evaluation shows positive results in all metrics by employing domain adaptation, demonstrating strong performance on QA tasks and providing insights into their efficacy in reducing hallucinations. Our findings clearly indicate that domain adaptation not only enhances the models' performance on QA tasks but also significantly reduces hallucination across all evaluated RAG architectures.

As millions of Muslims turn to LLMs like GPT, Claude, and DeepSeek for religious guidance, a critical question arises: Can these AI systems reliably reason about Islamic law? We introduce IslamicLegalBench, the first benchmark evaluating LLMs across seven schools of Islamic jurisprudence, with 718 instances covering 13 tasks of varying complexity. Evaluation of nine state-of-the-art models reveals major limitations: the best model achieves only 68% correctness with 21% hallucination, while several models fall below 35% correctness and exceed 55% hallucination. Few-shot prompting provides minimal gains, improving only 2 of 9 models by >1%. Moderate-complexity tasks requiring exact knowledge show the highest errors, whereas high-complexity tasks display apparent competence through semantic reasoning. False premise detection indicates risky sycophancy, with 6 of 9 models accepting misleading assumptions at rates above 40%. These results highlight that prompt-based methods cannot compensate for missing foundational knowledge. IslamicLegalBench offers the first systematic framework to evaluate Islamic legal reasoning in AI, revealing critical gaps in tools increasingly relied on for spiritual guidance.

Large language models (LLMs) have enabled powerful advances in natural language understanding and generation. Yet their application to complex, real-world scientific workflows remain limited by challenges in memory, planning, and tool integration. Here, we introduce SciBORG (Scientific Bespoke Artificial Intelligence Agents Optimized for Research Goals), a modular agentic framework that allows LLM-based agents to autonomously plan, reason, and achieve robust and reliable domain-specific task execution. Agents are constructed dynamically from source code documentation and augmented with finite-state automata (FSA) memory, enabling persistent state tracking and context-aware decision-making. This approach eliminates the need for manual prompt engineering and allows for robust, scalable deployment across diverse applications via maintaining context across extended workflows and to recover from tool or execution failures. We validate SciBORG through integration with both physical and virtual hardware, such as microwave synthesizers for executing user-specified reactions, with context-aware decision making and demonstrate its use in autonomous multi-step bioassay retrieval from the PubChem database utilizing multi-step planning, reasoning, agent-to-agent communication and coordination for execution of exploratory tasks. Systematic benchmarking shows that SciBORG agents achieve reliable execution, adaptive planning, and interpretable state transitions. Our results show that memory and state awareness are critical enablers of agentic planning and reliability, offering a generalizable foundation for deploying AI agents in complex environments.

Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes. As large language models demonstrate advanced capabilities in reasoning, coding, and engineering tasks, it is increasingly important to understand whether they can discover such methods rather than only apply existing ones. We introduce MLS-Bench, a benchmark for evaluating whether AI systems can invent generalizable and scalable ML methods. MLS-Bench contains 140 tasks across 12 domains, each requiring an agent to improve one targeted component of an ML system or algorithm and demonstrate that the improvement generalizes across controlled settings and scales. We find that current agents remain far from reliably surpassing human-designed methods, and that engineering-style tuning is easier for them than genuine method invention. We further study the effects of test-time scaling, adaptive compute allocation, and context provision on agents' discovery performance, together with case studies of their behavior. Our analyses suggest that the bottleneck is not only in proposing new methods, but also in the scientific insight needed to plan, validate, and scale claims about them. More search, compute, or context alone does not remove this bottleneck. We build and maintain a community platform for cumulative and comparable iteration, and release the data and code at https://mls-bench.com.

Despite advances in AI's performance and interpretability, AI advisors can undermine experts' decisions and increase the time and effort experts must invest to make decisions. Consequently, AI systems deployed in high-stakes settings often fail to consistently add value across contexts and can even diminish the value that experts alone provide. Beyond harm in specific domains, such outcomes impede progress in research and practice, underscoring the need to understand when and why different AI advisors add or diminish value. To bridge this gap, we stress the importance of assessing the value AI advice brings to real-world contexts when designing and evaluating AI advisors. Building on this perspective, we characterize key pillars -- pathways through which AI advice impacts value -- and develop a framework that incorporates these pillars to create reliable, personalized, and value-adding advisors. Our results highlight the need for system-level, value-driven development of AI advisors that advise selectively, are tailored to experts' unique behaviors, and are optimized for context-specific trade-offs between decision improvements and advising costs. They also reveal how the lack of inclusion of these pillars in the design of AI advising systems may be contributing to the failures observed in practical applications.

Over the last decade, explainable AI has primarily focused on interpreting individual model predictions, producing post-hoc explanations that relate inputs to outputs under a fixed decision structure. Recent advances in large language models (LLMs) have enabled agentic AI systems whose behaviour unfolds over multi-step trajectories. In these settings, success and failure are determined by sequences of decisions rather than a single output. While useful, it remains unclear how explanation approaches designed for static predictions translate to agentic settings where behaviour emerges over time. In this work, we bridge the gap between static and agentic explainability by comparing attribution-based explanations with trace-based diagnostics across both settings. To make this distinction explicit, we empirically compare attribution-based explanations used in static classification tasks with trace-based diagnostics used in agentic benchmarks (TAU-bench Airline and AssistantBench). Our results show that while attribution methods achieve stable feature rankings in static settings (Spearman ρ= 0.86), they cannot be applied reliably to diagnose execution-level failures in agentic trajectories. In contrast, trace-grounded rubric evaluation for agentic settings consistently localizes behaviour breakdowns and reveals that state tracking inconsistency is 2.7times more prevalent in failed runs and reduces success probability by 49\%. These findings motivate a shift towards trajectory-level explainability for agentic systems when evaluating and diagnosing autonomous AI behaviour. Resources: https://github.com/VectorInstitute/unified-xai-evaluation-framework https://vectorinstitute.github.io/unified-xai-evaluation-framework

To apply eyeshadow without a brush, should I use a cotton swab or a toothpick? Questions requiring this kind of physical commonsense pose a challenge to today's natural language understanding systems. While recent pretrained models (such as BERT) have made progress on question answering over more abstract domains - such as news articles and encyclopedia entries, where text is plentiful - in more physical domains, text is inherently limited due to reporting bias. Can AI systems learn to reliably answer physical common-sense questions without experiencing the physical world? In this paper, we introduce the task of physical commonsense reasoning and a corresponding benchmark dataset Physical Interaction: Question Answering or PIQA. Though humans find the dataset easy (95% accuracy), large pretrained models struggle (77%). We provide analysis about the dimensions of knowledge that existing models lack, which offers significant opportunities for future research.

We examine two properties of AI systems: capability (what a system can do) and steerability (how reliably one can shift behavior toward intended outcomes). A central question is whether capability growth reduces steerability and risks control collapse. We also distinguish between authorized steerability (builders reliably reaching intended behaviors) and unauthorized steerability (attackers eliciting disallowed behaviors). This distinction highlights a fundamental safety--security dilemma of AI models: safety requires high steerability to enforce control (e.g., stop/refuse), while security requires low steerability for malicious actors to elicit harmful behaviors. This tension presents a significant challenge for open-weight models, which currently exhibit high steerability via common techniques like fine-tuning or adversarial attacks. Using Qwen3 and InstrumentalEval, we find that a short anti-instrumental prompt suffix sharply reduces the measured convergence rate (e.g., shutdown avoidance, self-replication). For Qwen3-30B Instruct, the convergence rate drops from 81.69% under a pro-instrumental suffix to 2.82% under an anti-instrumental suffix. Under anti-instrumental prompting, larger aligned models show lower convergence rates than smaller ones (Instruct: 2.82% vs. 4.23%; Thinking: 4.23% vs. 9.86%). Code is available at github.com/j-hoscilowicz/instrumental_steering.

A critical gap exists between the general-purpose visual understanding of state-of-the-art physical AI models and the specialized perceptual demands of structured real-world deployment environments. We present PRISM, a 270K-sample multi-view video supervised fine-tuning (SFT) corpus for embodied vision-language-models (VLMs) in real-world retail environments. PRISM is motivated by a simple observation - physical AI systems fail not because of poor visual recognition, but because they do not understand space, physical dynamics and embodied action well enough to operate reliably in the world. To this end, PRISM is grounded in a novel three-dimensional knowledge ontology that spans spatial knowledge, temporal and physical knowledge, and embodied action knowledge. It covers 20+ capability probes across four evaluation dimensions - Embodied Reasoning (ER), Common Sense (CS), Spatial Perception (SP), and Intuitive Physics (IP), and to our knowledge, PRISM is the first dataset to instantiate all three knowledge dimensions within a single real-world deployment domain. The corpus captures data from egocentric, exocentric and 360° viewpoints across five supermarket locations and includes open-ended, chain-of-thought, and multiple-choice supervision. At 4 fps, PRISM spans approximately 11.8M video frames and approximately 730M tokens, placing it among the largest domain-specific video SFT corpora. Fine-tuning on PRISM reduces the error rate across all 20+ probes by 66.6% over the pre-trained baseline, with significant gains in embodied action understanding where the accuracy improves by 36.4%. Our results suggest that ontology-structured, domain specific SFT can meaningfully strengthen embodied VLMs for real-world settings. The PRISM dataset and more details are available at https://dreamvu.ai/prism

We present GPQA, a challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. We ensure that the questions are high-quality and extremely difficult: experts who have or are pursuing PhDs in the corresponding domains reach 65% accuracy (74% when discounting clear mistakes the experts identified in retrospect), while highly skilled non-expert validators only reach 34% accuracy, despite spending on average over 30 minutes with unrestricted access to the web (i.e., the questions are "Google-proof"). The questions are also difficult for state-of-the-art AI systems, with our strongest GPT-4 based baseline achieving 39% accuracy. If we are to use future AI systems to help us answer very hard questions, for example, when developing new scientific knowledge, we need to develop scalable oversight methods that enable humans to supervise their outputs, which may be difficult even if the supervisors are themselves skilled and knowledgeable. The difficulty of GPQA both for skilled non-experts and frontier AI systems should enable realistic scalable oversight experiments, which we hope can help devise ways for human experts to reliably get truthful information from AI systems that surpass human capabilities.

Reinforcement Learning from Human Feedback (RLHF) is a crucial technique for aligning language models with human preferences, playing a pivotal role in the success of conversational models like GPT-4, ChatGPT, and Llama 2. A core challenge in employing RLHF lies in training a reliable reward model (RM), which relies on high-quality labels typically provided by human experts or advanced AI system. These methods can be costly and may introduce biases that affect the language model's responses. As language models improve, human input may become less effective in further enhancing their performance. In this paper, we propose Self-Evolved Reward Learning (SER), a novel approach where the RM generates additional training data to iteratively improve itself. We conducted extensive experiments on multiple datasets such as HH-RLHF and UltraFeedback, using models like Mistral and Llama 3, and compare SER against various baselines. Our results demonstrate that even with limited human-annotated data, learning from self-feedback can robustly enhance RM performance, thereby boosting the capabilities of large language models (LLMs).

The ability to acknowledge the inevitable uncertainty in their knowledge and reasoning is a prerequisite for AI systems to be truly truthful and reliable. In this paper, we present a taxonomy of uncertainty specific to vision-language AI systems, distinguishing between epistemic uncertainty (arising from a lack of information) and aleatoric uncertainty (due to inherent unpredictability), and further explore finer categories within. Based on this taxonomy, we synthesize a benchmark dataset, CertainlyUncertain, featuring 178K visual question answering (VQA) samples as contrastive pairs. This is achieved by 1) inpainting images to make previously answerable questions into unanswerable ones; and 2) using image captions to prompt large language models for both answerable and unanswerable questions. Additionally, we introduce a new metric confidence-weighted accuracy, that is well correlated with both accuracy and calibration error, to address the shortcomings of existing metrics.

Tool calling has emerged as a critical capability for AI agents to interact with the real world and solve complex tasks. While the Model Context Protocol (MCP) provides a powerful standardized framework for tool integration, there is a significant gap in benchmarking how well AI agents can effectively solve multi-step tasks using diverse MCP tools in realistic, dynamic scenarios. In this work, we present LiveMCP-101, a benchmark of 101 carefully curated real-world queries, refined through iterative LLM rewriting and manual review, that require coordinated use of multiple MCP tools including web search, file operations, mathematical reasoning, and data analysis. Moreover, we introduce a novel evaluation approach that leverages ground-truth execution plans rather than raw API outputs, better reflecting the evolving nature of real-world environments. Experiments show that even frontier LLMs achieve a success rate below 60\%, highlighting major challenges in tool orchestration. Detailed ablations and error analysis further reveal distinct failure modes and inefficiencies in token usage, pointing to concrete directions for advancing current models. LiveMCP-101 sets a rigorous standard for evaluating real-world agent capabilities, advancing toward autonomous AI systems that reliably execute complex tasks through tool use.

The large language model (LLM)-as-judge paradigm has been used to meet the demand for a cheap, reliable, and fast evaluation of model outputs during AI system development and post-deployment monitoring. While judge models -- LLMs finetuned to specialize in assessing and critiquing model outputs -- have been touted as general purpose evaluators, they are typically evaluated only on non-contextual scenarios, such as instruction following. The omission of contextual settings -- those where external information is used as context to generate an output -- is surprising given the increasing prevalence of retrieval-augmented generation (RAG) and summarization use cases. Contextual assessment is uniquely challenging, as evaluation often depends on practitioner priorities, leading to conditional evaluation criteria (e.g., comparing responses based on factuality and then considering completeness if they are equally factual). To address the gap, we propose ContextualJudgeBench, a judge benchmark with 2,000 challenging response pairs across eight splits inspired by real-world contextual evaluation scenarios. We build our benchmark with a multi-pronged data construction pipeline that leverages both existing human annotations and model-based perturbations. Our comprehensive study across 11 judge models and 9 general purpose models, reveals that the contextual information and its assessment criteria present a significant challenge to even state-of-the-art models. For example, OpenAI's o1, the best-performing model, barely reaches 55% consistent accuracy.

Truly reliable AI requires more than simply scaling up knowledge; it demands the ability to know what it knows and when it does not. Yet recent research shows that even the best LLMs misjudge their own competence in more than one in five cases, making any response born of such internal uncertainty impossible to fully trust. Inspired by self-improvement reinforcement learning techniques that require minimal data, we present a simple but powerful framework KnowRL that strengthens a model's internal understanding of its own feasibility boundaries, enabling safer and more responsible behaviour. Our framework combines two components: (i) introspection, where the model generates and classifies tasks it judges feasible or infeasible, and (ii) consensus-based rewarding, where stability of self-knowledge assessment is reinforced through internal agreement. By using internally generated data, this design strengthens consistency in self-knowledge and entirely avoids costly external supervision. In experiments on LLaMA-3.1-8B and Qwen-2.5-7B, KnowRL steadily improved self-knowledge, validated by both intrinsic self-consistency and extrinsic benchmarking. With nothing more than a small seed set and no external supervision, our method drove gains as high as 28% in accuracy and 12% in F1, outperforming baselines in just a few iterations. Our framework essentially unlocks the untapped capacity of LLMs to self-improve their knowledge awareness, opening the door to reliable, more accountable AI and safer deployment in critical applications. Owing to its simplicity and independence from external effort, we encourage applying this reliability-enhancing process to all future models.

Aerosol forecasting is essential for air quality warnings, health risk assessment, and climate change mitigation. However, it is more complex than weather forecasting due to the intricate interactions between aerosol physicochemical processes and atmospheric dynamics, resulting in significant uncertainty and high computational costs. Here, we develop an artificial intelligence-driven global aerosol-meteorology forecasting system (AI-GAMFS), which provides reliable 5-day, 3-hourly forecasts of aerosol optical components and surface concentrations at a 0.5° x 0.625° resolution. AI-GAMFS combines Vision Transformer and U-Net in a backbone network, robustly capturing the complex aerosol-meteorology interactions via global attention and spatiotemporal encoding. Trained on 42 years of advanced aerosol reanalysis data and initialized with GEOS Forward Processing (GEOS-FP) analyses, AI-GAMFS delivers operational 5-day forecasts in one minute. It outperforms the Copernicus Atmosphere Monitoring Service (CAMS) global forecasting system, GEOS-FP forecasts, and several regional dust forecasting systems in forecasting most aerosol variables including aerosol optical depth and dust components. Our results mark a significant step forward in leveraging AI to refine physics-based aerosol forecasting, facilitating more accurate global warnings for aerosol pollution events, such as dust storms and wildfires.

AI agents are increasingly deployed to execute important tasks. While rising accuracy scores on standard benchmarks suggest rapid progress, many agents still continue to fail in practice. This discrepancy highlights a fundamental limitation of current evaluations: compressing agent behavior into a single success metric obscures critical operational flaws. Notably, it ignores whether agents behave consistently across runs, withstand perturbations, fail predictably, or have bounded error severity. Grounded in safety-critical engineering, we provide a holistic performance profile by proposing twelve concrete metrics that decompose agent reliability along four key dimensions: consistency, robustness, predictability, and safety. Evaluating 14 agentic models across two complementary benchmarks, we find that recent capability gains have only yielded small improvements in reliability. By exposing these persistent limitations, our metrics complement traditional evaluations while offering tools for reasoning about how agents perform, degrade, and fail.

AI-assisted research is crossing a threshold: fully automated systems can now generate research papers for as little as $15, while long-horizon agents can execute experiments, draft manuscripts, and simulate critique with minimal human input. Yet this productivity frontier exposes a deeper integrity problem: under scientific pressure, even frontier LLMs still fabricate results, miss hidden errors, and fail to judge novelty reliably. Studying developments through April 2026, we present an end-to-end analysis of AI across the complete research lifecycle, organized into four epistemological phases: Creation (idea generation, literature review, coding & experiments, tables & figures), Writing (paper writing), Validation (peer review, rebuttal & revision), and Dissemination (posters, slides, videos, social media, project pages, and interactive agents). We identify a sharp, stage-dependent boundary between reliable assistance and unreliable autonomy: AI excels at structured, retrieval-grounded, and tool-mediated tasks, but remains fragile for genuinely novel ideas, research-level experiments, and scientific judgment. Generated ideas often degrade after implementation, research code lags far behind pattern-matching benchmarks, and end-to-end autonomous systems have not yet consistently reached major-venue acceptance standards. We further show that greater automation can obscure rather than eliminate failure modes, making human-governed collaboration the most credible deployment paradigm. Finally, we provide a structured taxonomy, benchmark suite, and tool inventory, cross-stage design principles, and a practitioner-oriented playbook, with resources maintained at our project page.

Reliable neural networks (NNs) provide important inference-time reliability guarantees such as fairness and robustness. Complementarily, privacy-preserving NN inference protects the privacy of client data. So far these two emerging areas have been largely disconnected, yet their combination will be increasingly important. In this work, we present the first system which enables privacy-preserving inference on reliable NNs. Our key idea is to design efficient fully homomorphic encryption (FHE) counterparts for the core algorithmic building blocks of randomized smoothing, a state-of-the-art technique for obtaining reliable models. The lack of required control flow in FHE makes this a demanding task, as na\"ive solutions lead to unacceptable runtime. We employ these building blocks to enable privacy-preserving NN inference with robustness and fairness guarantees in a system called Phoenix. Experimentally, we demonstrate that Phoenix achieves its goals without incurring prohibitive latencies. To our knowledge, this is the first work which bridges the areas of client data privacy and reliability guarantees for NNs.

Given a black-box AI system and a task, at what confidence level can a practitioner trust the system's output? We answer with a reliability level -- a single number per system-task pair, derived from self-consistency sampling and conformal calibration, that serves as a black-box deployment gate with exact, finite-sample, distribution-free guarantees. Self-consistency sampling reduces uncertainty exponentially; conformal calibration guarantees correctness within 1/(n+1) of the target level, regardless of the system's errors -- made transparently visible through larger answer sets for harder questions. Weaker models earn lower reliability levels (not accuracy -- see Definition 2.4): GPT-4.1 earns 94.6% on GSM8K and 96.8% on TruthfulQA, while GPT-4.1-nano earns 89.8% on GSM8K and 66.5% on MMLU. We validate across five benchmarks, five models from three families, and both synthetic and real data. Conditional coverage on solvable items exceeds 0.93 across all configurations; sequential stopping reduces API costs by around 50%.

In the age of open and free information, a concerning trend of reliance on AI is emerging. However, existing AI tools struggle to evaluate the credibility of information and to justify their assessments. Hence, there is a growing need for systems that can help users evaluate the trustworthiness of online information. Although major search engines incorporate AI features, they often lack clear reliability indicators. We present TrueGL, a model that makes trustworthy search results more accessible. The model is a fine-tuned version of IBM's Granite-1B, trained on the custom dataset and integrated into a search engine with a reliability scoring system. We evaluate the system using prompt engineering and assigning each statement a continuous reliability score from 0.1 to 1, then instructing the model to return a textual explanation alongside the score. Each model's predicted scores are measured against real scores using standard evaluation metrics. TrueGL consistently outperforms other small-scale LLMs and rule-based approaches across all experiments on key evaluation metrics, including MAE, RMSE, and R2. The model's high accuracy, broad content coverage, and ease of use make trustworthy information more accessible and help reduce the spread of false or misleading content online. Our code is publicly available at https://github.com/AlgazinovAleksandr/TrueGL, and our model is publicly released at https://huggingface.co/JoydeepC/trueGL.

Multi-agent systems powered by large language models (LLMs) are transforming enterprise automation, yet systematic evaluation methodologies for assessing tool-use reliability remain underdeveloped. We introduce a comprehensive diagnostic framework that leverages big data analytics to evaluate procedural reliability in intelligent agent systems, addressing critical needs for SME-centric deployment in privacy-sensitive environments. Our approach features a 12-category error taxonomy capturing failure modes across tool initialization, parameter handling, execution, and result interpretation. Through systematic evaluation of 1,980 deterministic test instances spanning both open-weight models (Qwen2.5 series, Functionary) and proprietary alternatives (GPT-4, Claude 3.5/3.7) across diverse edge hardware configurations, we identify actionable reliability thresholds for production deployment. Our analysis reveals that procedural reliability, particularly tool initialization failures, constitutes the primary bottleneck for smaller models, while qwen2.5:32b achieves flawless performance matching GPT-4.1. The framework demonstrates that mid-sized models (qwen2.5:14b) offer practical accuracy-efficiency trade-offs on commodity hardware (96.6\% success rate, 7.3 s latency), enabling cost-effective intelligent agent deployment for resource-constrained organizations. This work establishes foundational infrastructure for systematic reliability evaluation of tool-augmented multi-agent AI systems.

AI agents are actively running in production across diverse industries, yet little is publicly known about which technical approaches enable successful real-world deployments. We present the first large-scale systematic study of AI agents in production, surveying 306 practitioners and conducting 20 in-depth case studies via interviews across 26 domains. We investigate why organizations build agents, how they build them, how they evaluate them, and what the top development challenges are. We find that production agents are typically built using simple, controllable approaches: 68% execute at most 10 steps before requiring human intervention, 70% rely on prompting off-the-shelf models instead of weight tuning, and 74% depend primarily on human evaluation. Reliability remains the top development challenge, driven by difficulties in ensuring and evaluating agent correctness. Despite these challenges, simple yet effective methods already enable agents to deliver impact across diverse industries. Our study documents the current state of practice and bridges the gap between research and deployment by providing researchers visibility into production challenges while offering practitioners proven patterns from successful deployments.

This paper reviews Trustworthy Artificial Intelligence (TAI) and its various definitions. Considering the principles respected in any society, TAI is often characterized by a few attributes, some of which have led to confusion in regulatory or engineering contexts. We argue against using terms such as Responsible or Ethical AI as substitutes for TAI. And to help clarify any confusion, we suggest leaving them behind. Given the subjectivity and complexity inherent in TAI, developing a universal framework is deemed infeasible. Instead, we advocate for approaches centered on addressing key attributes and properties such as fairness, bias, risk, security, explainability, and reliability. We examine the ongoing regulatory landscape, with a focus on initiatives in the EU, China, and the USA. We recognize that differences in AI regulations based on geopolitical and geographical reasons pose an additional challenge for multinational companies. We identify risk as a core factor in AI regulation and TAI. For example, as outlined in the EU-AI Act, organizations must gauge the risk level of their AI products to act accordingly (or risk hefty fines). We compare modalities of TAI implementation and how multiple cross-functional teams are engaged in the overall process. Thus, a brute force approach for enacting TAI renders its efficiency and agility, moot. To address this, we introduce our framework Set-Formalize-Measure-Act (SFMA). Our solution highlights the importance of transforming TAI-aware metrics, drivers of TAI, stakeholders, and business/legal requirements into actual benchmarks or tests. Finally, over-regulation driven by panic of powerful AI models can, in fact, harm TAI too. Based on GitHub user-activity data, in 2023, AI open-source projects rose to top projects by contributor account. Enabling innovation in TAI hinges on the independent contributions of the open-source community.

Although demonstrating remarkable performance on reasoning tasks, Large Language Models (LLMs) still tend to fabricate unreliable responses when confronted with problems that are unsolvable or beyond their capability, severely undermining the reliability. Prior studies of LLM reliability have primarily focused on knowledge tasks to identify unanswerable questions, while mathematical reasoning tasks have remained unexplored due to the dearth of unsolvable math problems. To systematically investigate LLM reliability in mathematical reasoning tasks, we formulate the reliability evaluation for both solvable and unsolvable problems. We then develop a ReliableMath dataset which incorporates open-source solvable problems and high-quality unsolvable problems synthesized by our proposed construction workflow with human evaluations. Experiments are conducted on various LLMs with several key findings uncovered. LLMs fail to directly identify unsolvable problems and always generate fabricated responses. When instructing LLMs to indicate unsolvability using a reliable prompt, the reliability of larger-sized LLMs remains on solvable problems, but notably improves on unsolvable problems yet still falls short of solvable problems. However, small LLMs rarely show any progress despite employing reliable prompts. Therefore, we further propose an alignment strategy to enhance small LLMs' reliability, which can significantly improve LLM reliability performances on both in-domain and out-of-domain tasks.

AI Agents can perform complex operations at great speed, but just like all the humans we have ever hired, their intelligence remains fallible. Miscommunications aren't noticed, systemic biases have no counter-action, and inner monologues are rarely written down. We did not come to fire them for their mistakes, but to hire them and provide a safe productive working environment. We posit that we can reuse a common corporate organizational structure: teams of independent AI agents with strict role boundaries can work with common goals, but opposing incentives. Multiple models serving as a team of rivals can catch and minimize errors within the final product at a small cost to the velocity of actions. In this paper we demonstrate that we can achieve reliability without acquiring perfect components, but through careful orchestration of imperfect ones. This paper describes the architecture of such a system in practice: specialized agent teams (planners, executors, critics, experts), organized into an organization with clear goals, coordinated through a remote code executor that keeps data transformations and tool invocations separate from reasoning models. Rather than agents directly calling tools and ingesting full responses, they write code that executes remotely; only relevant summaries return to agent context. By preventing raw data and tool outputs from contaminating context windows, the system maintains clean separation between perception (brains that plan and reason) and execution (hands that perform heavy data transformations and API calls). We demonstrate the approach achieves over 90% internal error interception prior to user exposure while maintaining acceptable latency tradeoffs. A survey from our traces shows that we only trade off cost and latency to achieve correctness and incrementally expand capabilities without impacting existing ones.

Obtaining reliable feedback from the environment is a fundamental capability for intelligent agents to evaluate the correctness of their actions and to accumulate reusable knowledge. However, most existing approaches rely on predefined measurements or fixed reward signals, which limits their applicability in open-ended and dynamic environments where new actions may require previously unknown forms of feedback. To address these limitations, this paper proposes an Actively Feedback Getting model, in which an AI agent proactively interacts with the environment to discover, screen, and verify feedback without relying on predefined measurements. Rather than assuming explicit feedback definitions, the proposed method exploits action-induced environmental differences to identify target feedback that is not specified in advance, based on the observation that actions inevitably produce measurable changes in the environment. In addition, a self-triggering mechanism, driven by internal objectives such as improved accuracy, precision, and efficiency, is introduced to autonomously plan and adjust actions, thereby enabling faster and more focused feedback acquisition without external commands. Experimental results demonstrate that the proposed active approach significantly improves the efficiency and robustness of factor identification.

Large Reasoning Models (LRMs) exhibit strong performance, yet often produce rationales that sound plausible but fail to reflect their true decision process, undermining reliability and trust. We introduce a formal framework for reasoning faithfulness, defined by two testable conditions: stance consistency (a coherent stance linking reasoning to answer) and causal influence (the stated reasoning causally drives the answer under output-level interventions), explicitly decoupled from accuracy. To operationalize this, we present RFEval, a benchmark of 7,186 instances across seven tasks that probes faithfulness via controlled, output-level counterfactual interventions. Evaluating twelve open-source LRMs, we find unfaithfulness in 49.7% of outputs, predominantly from stance inconsistency. Failures are concentrated in brittle, convergent domains such as math and code, and correlate more with post-training regimes than with scale: within-family ablations indicate that adding current RL-style objectives on top of supervised fine-tuning can reduce reasoning faithfulness, even when accuracy is maintained. Crucially, accuracy is neither a sufficient nor a reliable proxy for faithfulness: once controlling for model and task, the accuracy-faithfulness link is weak and statistically insignificant. Our work establishes a rigorous methodology for auditing LRM reliability and shows that trustworthy AI requires optimizing not only for correct outcomes but also for the structural integrity of the reasoning process. Our code and dataset can be found at project page: https://aidaslab.github.io/RFEval/}{https://aidaslab.github.io/RFEval/

Large language models (LLMs) are increasingly used in interactive applications, and human evaluation remains the gold standard for assessing their performance in multi-turn conversations. Since human studies are costly, time-consuming, and hard to reproduce, recent work explores using LLMs to simulate users for automatic assistant evaluation. However, there is no benchmark or systematic study to evaluate whether these simulated users are reliable stand-ins for real users. To address this, we introduce SimulatorArena, a benchmark of 909 annotated human-LLM conversations on two interactive tasks -- math tutoring and document creation. SimulatorArena evaluates simulators based on how closely their messages match human behavior and how well their assistant ratings align with human judgments. Experiments on various simulator methods show that simulators conditioned on user profiles, capturing traits like background and message styles, align closely with human judgments. They reach Spearman's rho of 0.7 on both tasks, providing a practical, scalable alternative to human evaluation. Using the best simulator for each task, we benchmark 18 assistants, including the latest LLMs such as GPT-5, Claude 4.1 Opus, and Gemini 2.5 Pro.

Large language models (LLMs) power many interactive systems such as chatbots, customer-service agents, and personal assistants. In knowledge-intensive scenarios requiring user-specific personalization, conventional retrieval-augmented generation (RAG) pipelines exhibit limited memory capacity and insufficient coordination between retrieval mechanisms and user-specific conversational history, leading to redundant clarification, irrelevant documents, and degraded user experience. Inspired by the hippocampus-neocortex memory mechanism, we propose HiMeS, an AI-assistant architecture that fuses short-term and long-term memory. Our contributions are fourfold: (1) A short-term memory extractor is trained end-to-end with reinforcement learning to compress recent dialogue and proactively pre-retrieve documents from the knowledge base, emulating the cooperative interaction between the hippocampus and prefrontal cortex. (2) A partitioned long-term memory network stores user-specific information and re-ranks retrieved documents, simulating distributed cortical storage and memory reactivation. (3) On a real-world industrial dataset, HiMeS significantly outperforms a cascaded RAG baseline on question-answering quality. (4) Ablation studies confirm the necessity of both memory modules and suggest a practical path toward more reliable, context-aware, user-customized LLM-based assistants.

KT developed a Responsible AI (RAI) assessment methodology and risk mitigation technologies to ensure the safety and reliability of AI services. By analyzing the Basic Act on AI implementation and global AI governance trends, we established a unique approach for regulatory compliance and systematically identify and manage all potential risk factors from AI development to operation. We present a reliable assessment methodology that systematically verifies model safety and robustness based on KT's AI risk taxonomy tailored to the domestic environment. We also provide practical tools for managing and mitigating identified AI risks. With the release of this report, we also release proprietary Guardrail : SafetyGuard that blocks harmful responses from AI models in real-time, supporting the enhancement of safety in the domestic AI development ecosystem. We also believe these research outcomes provide valuable insights for organizations seeking to develop Responsible AI.

The use of large language models (LLMs) for automated code generation has emerged as a significant focus within AI research. As these pretrained models continue to evolve, their ability to understand and generate complex code structures has opened new possibilities for automating intricate programming tasks for the sake of accurate code generation. Although contemporary foundational models demonstrate promoting results, researchers continue to explore optimal post-training strategies to enhance code quality. These include supervised fine-tuning, retrieval-augmented generation (RAG), debugging, and many others. In this paper, we combine two widely used approaches namely multi-agent collaboration and runtime execution information-based debugging, for improving code generation functionality, reliability, and practical applicability. We perform an empirical study in order to extend the evaluation of the individual strategies as well as the proposed composition of the activities of both strategies. Our study use 19 LLMs to examines the performance of individual and the proposed strategies, offering comprehensive insights into how different programming activities compositions and training paradigms influence code generation effectiveness. In particular, we implement a chained system that combines both strategies to assess their combined impact on functional accuracy, code reliability, and generation latency using two benchmark datasets commonly used for code generation. Our findings provide valuable insights for organizations seeking robust AI-driven coding solutions by guiding them in selecting models that can better adapt to complex post-training strategies, ultimately fostering the adoption of more effective and reliable code generation technologies.

Multi-agent LLM ensembles can converge on coordinated, socially harmful equilibria. This paper advances an experimental framework for evaluating Institutional AI, our system-level approach to AI alignment that reframes alignment from preference engineering in agent-space to mechanism design in institution-space. Central to this approach is the governance graph, a public, immutable manifest that declares legal states, transitions, sanctions, and restorative paths; an Oracle/Controller runtime interprets this manifest, attaching enforceable consequences to evidence of coordination while recording a cryptographically keyed, append-only governance log for audit and provenance. We apply the Institutional AI framework to govern the Cournot collusion case documented by prior work and compare three regimes: Ungoverned (baseline incentives from the structure of the Cournot market), Constitutional (a prompt-only policy-as-prompt prohibition implemented as a fixed written anti-collusion constitution, and Institutional (governance-graph-based). Across six model configurations including cross-provider pairs (N=90 runs/condition), the Institutional regime produces large reductions in collusion: mean tier falls from 3.1 to 1.8 (Cohen's d=1.28), and severe-collusion incidence drops from 50% to 5.6%. The prompt-only Constitutional baseline yields no reliable improvement, illustrating that declarative prohibitions do not bind under optimisation pressure. These results suggest that multi-agent alignment may benefit from being framed as an institutional design problem, where governance graphs can provide a tractable abstraction for alignment-relevant collective behavior.