HyperGraphPro: Progress-Aware Reinforcement Learning for Structure-Guided Hypergraph RAG

TL;DR

HyperGraphPro enhances graph retrieval for large language models by integrating structure-aware hypergraph traversal and progress-based reinforcement learning, leading to better multi-hop reasoning and answer accuracy.

Contribution

It introduces a novel structure-aware hypergraph retrieval mechanism and a progress-based policy optimization for improved multi-step reasoning in GraphRAG.

Findings

Improves reasoning accuracy on multi-hop question answering benchmarks.

Enhances generation quality compared to existing GraphRAG methods.

Promotes coherent multi-hop traversal through structure-aware retrieval.

Abstract

Graph Retrieval-Augmented Generation (GraphRAG) has emerged as a promising paradigm that organizes external knowledge into structured graphs of entities and relations, enabling large language models (LLMs) to perform complex reasoning beyond text-chunk retrieval. Recent advances have integrated reinforcement learning (RL) into agentic GraphRAG approaches, enabling iterative interactions with knowledge graphs during training. However, existing RL-based methods suffer from two key limitations: (1) they primarily depend on semantic similarity for retrieval, often overlooking the underlying graph topology, and (2) they rely on sparse, outcome-level rewards that fail to capture the quality of intermediate retrieval steps and their dependencies. To address these limitations, we propose HyperGraphPro, a progress-aware agentic framework for graph-based retrieval and multi-step reasoning. HyperGraphPro introduces a structure-aware hypergraph retrieval mechanism that jointly considers semantic relevance and graph connectivity, promoting coherent traversal along multi-hop reasoning paths. Furthermore, we design a progress-based stepwise policy optimization that provides dense learning signals by modulating advantages according to intermediate reasoning progress within a graph, rather than relying solely on final outcomes. Experiments on multi-hop question answering benchmarks demonstrate that HyperGraphPro consistently improves reasoning accuracy and generation quality over existing GraphRAG methods.