Retrieving Minimal and Sufficient Reasoning Subgraphs with Graph Foundation Models for Path-aware GraphRAG

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yuan, Haonan, Sun, Qingyun, Shi, Junhua, Liu, Mingjun, Yuan, Jiaqi, Zhang, Ziwei, Fu, Xingcheng, Li, Jianxin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912951465672704
author Yuan, Haonan
Sun, Qingyun
Shi, Junhua
Liu, Mingjun
Yuan, Jiaqi
Zhang, Ziwei
Fu, Xingcheng
Li, Jianxin
author_facet Yuan, Haonan
Sun, Qingyun
Shi, Junhua
Liu, Mingjun
Yuan, Jiaqi
Zhang, Ziwei
Fu, Xingcheng
Li, Jianxin
contents Graph-based retrieval-augmented generation (GraphRAG) exploits structured knowledge to support knowledge-intensive reasoning. However, most existing methods treat graphs as intermediate artifacts, and the few subgraph-based retrieval methods depend on heuristic rules coupled with domain-specific distributions. They fail in typical cold-start scenarios where data in target domains is scarce, thus yielding reasoning contexts that are either informationally incomplete or structurally redundant. In this work, we revisit retrieval from a structural perspective, and propose GFM-Retriever that directly responds to user queries with a subgraph, where a pre-trained Graph Foundation Model acts as a cross-domain Retriever for multi-hop path-aware reasoning. Building on this perspective, we repurpose a pre-trained GFM from an entity ranking function into a generalized retriever to support cross-domain retrieval. On top of the retrieved graph, we further derive a label-free subgraph selector optimized by a principled Information Bottleneck objective to identify the query-conditioned subgraph, which contains informationally sufficient and structurally minimal golden evidence in a self-contained "core set". To connect structure with generation, we explicitly extract and reorganize relational paths as in-context prompts, enabling interpretable reasoning. Extensive experiments on multi-hop question answering benchmarks demonstrate that GFM-Retriever achieves state-of-the-art performance in both retrieval quality and answer generation, while maintaining efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2603_07179
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Retrieving Minimal and Sufficient Reasoning Subgraphs with Graph Foundation Models for Path-aware GraphRAG
Yuan, Haonan
Sun, Qingyun
Shi, Junhua
Liu, Mingjun
Yuan, Jiaqi
Zhang, Ziwei
Fu, Xingcheng
Li, Jianxin
Information Retrieval
Graph-based retrieval-augmented generation (GraphRAG) exploits structured knowledge to support knowledge-intensive reasoning. However, most existing methods treat graphs as intermediate artifacts, and the few subgraph-based retrieval methods depend on heuristic rules coupled with domain-specific distributions. They fail in typical cold-start scenarios where data in target domains is scarce, thus yielding reasoning contexts that are either informationally incomplete or structurally redundant. In this work, we revisit retrieval from a structural perspective, and propose GFM-Retriever that directly responds to user queries with a subgraph, where a pre-trained Graph Foundation Model acts as a cross-domain Retriever for multi-hop path-aware reasoning. Building on this perspective, we repurpose a pre-trained GFM from an entity ranking function into a generalized retriever to support cross-domain retrieval. On top of the retrieved graph, we further derive a label-free subgraph selector optimized by a principled Information Bottleneck objective to identify the query-conditioned subgraph, which contains informationally sufficient and structurally minimal golden evidence in a self-contained "core set". To connect structure with generation, we explicitly extract and reorganize relational paths as in-context prompts, enabling interpretable reasoning. Extensive experiments on multi-hop question answering benchmarks demonstrate that GFM-Retriever achieves state-of-the-art performance in both retrieval quality and answer generation, while maintaining efficiency.
title Retrieving Minimal and Sufficient Reasoning Subgraphs with Graph Foundation Models for Path-aware GraphRAG
topic Information Retrieval
url https://arxiv.org/abs/2603.07179