Saved in:
Bibliographic Details
Main Authors: Yu, Chuanyue, Zhao, Kuo, Li, Yuhan, Chang, Heng, Feng, Mingjian, Jiang, Xiangzhe, Sun, Yufei, Li, Jia, Zhang, Yuzhi, Li, Jianxin, Zhang, Ziwei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.23581
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910001464868864
author Yu, Chuanyue
Zhao, Kuo
Li, Yuhan
Chang, Heng
Feng, Mingjian
Jiang, Xiangzhe
Sun, Yufei
Li, Jia
Zhang, Yuzhi
Li, Jianxin
Zhang, Ziwei
author_facet Yu, Chuanyue
Zhao, Kuo
Li, Yuhan
Chang, Heng
Feng, Mingjian
Jiang, Xiangzhe
Sun, Yufei
Li, Jia
Zhang, Yuzhi
Li, Jianxin
Zhang, Ziwei
contents Graph Retrieval-Augmented Generation (GraphRAG) has shown great effectiveness in enhancing the reasoning abilities of LLMs by leveraging graph structures for knowledge representation and modeling complex real-world relationships. However, existing GraphRAG methods still face significant bottlenecks when handling complex problems that require multi-hop reasoning, as their query and retrieval phases are largely based on pre-defined heuristics and do not fully utilize the reasoning potentials of LLMs. To address this problem, we propose GraphRAG-R1, an adaptive GraphRAG framework by training LLMs with process-constrained outcome-based reinforcement learning (RL) to enhance the multi-hop reasoning ability. Our method can decompose complex problems, autonomously invoke retrieval tools to acquire necessary information, and perform effective reasoning. Specifically, we utilize a modified version of Group Relative Policy Optimization (GRPO) that supports rollout-with-thinking capability. Next, we design two process-constrained reward functions. To handle the shallow retrieval problem, we design a Progressive Retrieval Attenuation (PRA) reward to encourage essential retrievals. Then, to handle the over-thinking problem, we design Cost-Aware F1 (CAF) reward to balance the model performance with computational costs. We further design a phase-dependent training strategy, containing three training stages corresponding to cold start and these two rewards. Lastly, our method adopts a hybrid graph-textual retrieval to improve the reasoning capacity. Extensive experimental results demonstrate that GraphRAG-R1 boosts LLM capabilities in solving complex reasoning problems compared to state-of-the-art GraphRAG methods on both in-domain and out-of-domain datasets. Furthermore, our framework can be flexibly integrated with various existing retrieval methods, consistently delivering performance improvements.
format Preprint
id arxiv_https___arxiv_org_abs_2507_23581
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GraphRAG-R1: Graph Retrieval-Augmented Generation with Process-Constrained Reinforcement Learning
Yu, Chuanyue
Zhao, Kuo
Li, Yuhan
Chang, Heng
Feng, Mingjian
Jiang, Xiangzhe
Sun, Yufei
Li, Jia
Zhang, Yuzhi
Li, Jianxin
Zhang, Ziwei
Machine Learning
Graph Retrieval-Augmented Generation (GraphRAG) has shown great effectiveness in enhancing the reasoning abilities of LLMs by leveraging graph structures for knowledge representation and modeling complex real-world relationships. However, existing GraphRAG methods still face significant bottlenecks when handling complex problems that require multi-hop reasoning, as their query and retrieval phases are largely based on pre-defined heuristics and do not fully utilize the reasoning potentials of LLMs. To address this problem, we propose GraphRAG-R1, an adaptive GraphRAG framework by training LLMs with process-constrained outcome-based reinforcement learning (RL) to enhance the multi-hop reasoning ability. Our method can decompose complex problems, autonomously invoke retrieval tools to acquire necessary information, and perform effective reasoning. Specifically, we utilize a modified version of Group Relative Policy Optimization (GRPO) that supports rollout-with-thinking capability. Next, we design two process-constrained reward functions. To handle the shallow retrieval problem, we design a Progressive Retrieval Attenuation (PRA) reward to encourage essential retrievals. Then, to handle the over-thinking problem, we design Cost-Aware F1 (CAF) reward to balance the model performance with computational costs. We further design a phase-dependent training strategy, containing three training stages corresponding to cold start and these two rewards. Lastly, our method adopts a hybrid graph-textual retrieval to improve the reasoning capacity. Extensive experimental results demonstrate that GraphRAG-R1 boosts LLM capabilities in solving complex reasoning problems compared to state-of-the-art GraphRAG methods on both in-domain and out-of-domain datasets. Furthermore, our framework can be flexibly integrated with various existing retrieval methods, consistently delivering performance improvements.
title GraphRAG-R1: Graph Retrieval-Augmented Generation with Process-Constrained Reinforcement Learning
topic Machine Learning
url https://arxiv.org/abs/2507.23581