{"ID":2889251,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.21892","arxiv_id":"2507.21892","title":"Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2507.21892","url_pdf":"https://arxiv.org/pdf/2507.21892v1","authors":"[\"Haoran Luo\",\"Haihong E\",\"Guanting Chen\",\"Qika Lin\",\"Yikai Guo\",\"Fangzhi Xu\",\"Zemin Kuang\",\"Meina Song\",\"Xiaobao Wu\",\"Yifan Zhu\",\"Luu Anh Tuan\"]","published":"2025-07-29T15:01:26Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"RAG\",\"Reinforcement Learning\",\"Large Language Model\"]","has_code":false}