UR$^2$: Unify RAG and Reasoning through Reinforcement Learning 文章

ArXiv CS.CL2026-06-03NEWSen作者: Weitao Li, Boran Xiang, Xiaolong Wang, Zhinan Gou, Weizhi Ma, Yang Liu

查看原文 →

UR$^2$: Unify RAG and Reasoning through Reinforcement Learning · 相关技术

相关技术

UR$^2$RLVR RAG LLM Reinforcement Learning from Verifiable Rewards Retrieval-Augmented Generation large language models