作者位次 #4/7ACL 2026Findings· Findings of ACL
R oute RAG : Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning
Yucan Guo · Miao Su · Saiping Guan · Zihao Sun · Xiaolong Jin · Jiafeng Guo · Xueqi Cheng
摘要
Retrieval-Augmented Generation (RAG) integrates non-parametric knowledge into Large Language Models (LLMs), typically from unstructured texts and structured graphs. While recent progress has advanced text-based RAG to multi-turn reasoning through Reinforcement Learning (RL), extending these advan...