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

TL;DR

This paper introduces GFM-Retriever, a novel method using pre-trained Graph Foundation Models to retrieve minimal, sufficient reasoning subgraphs for path-aware reasoning, improving multi-hop question answering performance.

Contribution

It proposes a cross-domain retrieval approach with a label-free subgraph selector optimized by an Information Bottleneck, enabling interpretable and efficient reasoning.

Findings

Achieves state-of-the-art retrieval quality on multi-hop QA benchmarks.

Demonstrates improved reasoning efficiency and interpretability.

Maintains high performance while being computationally efficient.

Abstract

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.