[논문리뷰] From Proof to Program: Characterizing Tool-Induced Reasoning Hallucinations in Large Language ModelsarXiv에 게시된 'From Proof to Program: Characterizing Tool-Induced Reasoning Hallucinations in Large Language Models' 논문에 대한 자세한 리뷰입니다.#Review#Tool-augmented LLMs#Reasoning Hallucinations#Tool-Induced Myopia (TIM)#Code Interpreter#Mathematical Reasoning#LLM Evaluation#Preference Optimization2025년 11월 16일댓글 수 로딩 중
[논문리뷰] rStar2-Agent: Agentic Reasoning Technical ReportWeijiang Xu이 arXiv에 게시한 'rStar2-Agent: Agentic Reasoning Technical Report' 논문에 대한 자세한 리뷰입니다.#Review#Agentic Reinforcement Learning#Math Reasoning#Code Interpreter#Tool Use#GRPO-RoC#LLM Training Efficiency#Self-Reflection2025년 8월 29일댓글 수 로딩 중