RecoWorld: Building Simulated Environments for Agentic Recommender Systems Paper • 2509.10397 • Published Sep 12, 2025 • 7
UOUO: Uncontextualized Uncommon Objects for Measuring Knowledge Horizons of Vision Language Models Paper • 2407.18391 • Published Jul 25, 2024
Circuit Tracing in Vision-Language Models: Understanding the Internal Mechanisms of Multimodal Thinking Paper • 2602.20330 • Published Feb 23
The Last Human-Written Paper: Agent-Native Research Artifacts Paper • 2604.24658 • Published 26 days ago • 21
Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning Paper • 2605.22642 • Published 4 days ago • 33
VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use Paper • 2505.19255 • Published May 25, 2025 • 5
Cache-of-Thought: Master-Apprentice Framework for Cost-Effective Vision Language Model Inference Paper • 2502.20587 • Published Feb 27, 2025 • 1
Aha Moment Revisited: Are VLMs Truly Capable of Self Verification in Inference-time Scaling? Paper • 2506.17417 • Published Jun 20, 2025 • 11