Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning
Nanyang Technological University, Singapore · Beijing University of Posts and Telecommunications · National University of Singapore · Beijing Institute of Computer Technology and Application · Xi'an Jiaotong University · Capital Medical University · Shanghai Jiaotong University · Nanyang Technological University
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
Retrieval-Augmented Generation (RAG) mitigates hallucination in LLMs by incorporating external knowledge, but relies on chunk-based retrieval that lacks structural semantics. GraphRAG methods improve RAG by modeling knowledge as entity-relation graphs, but still face challenges in high construction cost, fixed one-time retrieval, and reliance on long-context reasoning and prompt design. To address these challenges, we propose Graph-R1, an agentic GraphRAG framework via end-to-end reinforcement learning (RL). It introduces lightweight knowledge hypergraph construction, models retrieval as a multi-turn agent-environment interaction, and optimizes the agent process via an end-to-end reward mechanism. Experiments on standard RAG datasets show that Graph-R1 outperforms traditional GraphRAG and RL-enhanced RAG methods in reasoning accuracy, retrieval efficiency, and generation quality. Our code is available.