作者位次 #8/9ACL 2026Findings· Findings of ACL
R -Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning
Qingfei Zhao · Ruobing Wang · Dingling Xu · Daren Zha · Ma Bowen · Zhichun Wang · Shijie Jia · Limin Liu · Xin Wang
摘要
Large language models (LLMs) have notably progressed in multi-step and long-chain reasoning. However, extending their reasoning capabilities to encompass deep interactions with search remains a non-trivial challenge, as models often fail to identify optimal reasoning–search interaction trajectori...