Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation 事件

Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation arXiv:2510.13272v3 Announce Type: replace Abstract: Inspired by the success of reinforcement learning (RL) in Large Language Model (LLM) training for domains like math and code, recent work has begun training LLMs to dynamically plan, query, and reason with search engines as tools -- a paradigm increasingly referred to as agentic search. Although these methods achieve performance improvement across popular short-