Takashi Ishida's picture

4

Takashi Ishida

tksii

·

https://takashiishida.github.io

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies

upvoted a paper 15 days ago

Mitigating Reward Hacking in RLHF via Advantage Sign Robustness

authored a paper 16 days ago

Mitigating Reward Hacking in RLHF via Advantage Sign Robustness

View all activity

Organizations

upvoted a paper 1 day ago

CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies

Paper • 2606.16613 • Published 12 days ago • 7

upvoted a paper 15 days ago

Mitigating Reward Hacking in RLHF via Advantage Sign Robustness

Paper • 2604.02986 • Published Apr 3 • 3

upvoted 2 papers 17 days ago

How Can I Publish My LLM Benchmark Without Giving the True Answers Away?

Paper • 2505.18102 • Published May 23, 2025 • 2

Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests

Paper • 2606.07379 • Published 22 days ago • 5