作者位次 #4/7ACL 2026Poster· Natural Language Processing
Enhancing LLM -based Search Agents via Contribution Weighted Group Relative Policy Optimization
Junzhe Wang · Zhiheng Xi · yajie yang · Hao Luo · Shihan Dou · Tao Gui · Qi Zhang
摘要
Search agents extend Large Language Models (LLMs) beyond static parametric knowledge by enabling access to up-to-date and long-tail information unavailable during pretraining. While reinforcement learning has been widely adopted for training such agents, existing approaches face key limitations:...