aiqbench analysis
This paper introduces NexusRAG, a novel method that enhances graph-based retrieval-augmented generation by incorporating corpus-level entity neighborhoods to improve multi-hop reasoning. By guiding dual propagation paths between semantic and structural entities, the approach significantly boosts evidence recall on complex benchmarks compared to relation-free baselines. The work addresses critical limitations in current RAG systems where low query similarity often excludes vital bridging information necessary for accurate long-chain inference.
Corpus-Guided Dual-Path Propagation for Graph Retrieval-Augmented Generation
arXiv:2609.37661v1 Announce Type: new Abstract: Graph-based retrieval-augmented generation supports multi-hop retrieval by organizing corpus information into graphs. However, existing relation-free graph retrieval methods rely primarily on query-sentence similarity to search for evidence. This can exclude useful bridging evidence with low query similarity and activate incidental entities unrelated to the reasoning chain. In this paper, we propose a simple and effective approach called NexusRAG, which augments the relation-free Tri-Graph with a corpus-level entity neighborhood structure derived from joint entity co-occurrence and semantic similarity. NexusRAG employs this structure to guide two complementary propagation paths: neighborhood-constrained semantic propagation through sentences identifies the query-relevant entity frontier, while direct structural propagation between neighboring entities expands that frontier to structurally related entities. The propagated entity weights also inform neighborhood-aware passage initialization for Personalized PageRank. Experiments on three multi-hop QA benchmarks and a domain-specific subset of GraphRAG-Bench show that NexusRAG consistently outperforms existing approaches. On the GraphRAG-Bench subset, NexusRAG achieves the highest evidence recall in all question categories, exceeding baselines by 4.2-8.1 points. The implementation code is available at https://github.com/Jacob-biu/NexusRAG.
Abstract:Graph-based retrieval-augmented generation supports multi-hop retrieval by organizing corpus information into graphs. However, existing relation-free graph retrieval methods rely primarily on query-sentence similarity to search for evidence. This can exclude useful bridging evidence with low query similarity and activate incidental entities unrelated to the reasoning chain. In this paper, we propose a simple and effective approach called NexusRAG, which augments the relation-free Tri-Graph with a corpus-level entity neighborhood structure derived from joint entity co-occurrence and semantic similarity. NexusRAG employs this structure to guide two complementary propagation paths: neighborhood-constrained semantic propagation through sentences identifies the query-relevant entity frontier, while direct structural propagation between neighboring entities expands that frontier to structurally related entities. The propagated entity weights also inform neighborhood-aware passage initialization for Personalized PageRank. Experiments on three multi-hop QA benchmarks and a domain-specific subset of GraphRAG-Bench show that NexusRAG consistently outperforms existing approaches. On the GraphRAG-Bench subset, NexusRAG achieves the highest evidence recall in all question categories, exceeding baselines by 4.2-8.1 points. The implementation code is available at this https URL.
Computation and Language (cs.CL)
arXiv:2609.37661 [cs.CL]
(or arXiv:2609.37661v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.37661 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 265 words
Related coverage
From Vector Search to Agentic RAG: Building an Enterprise Research Analyst with hipVS
AMD · Jul 15, 2026
HyCE-RAG: Hypergraph Chain-of-Evidence Retrieval-Augmented Generation for Explainable Multi-hop Question Answering
arXiv · Jul 28, 2026
From Document Silos to Process Intelligence: A Multi-Layer Knowledge Graph for CMC Process Development
arXiv · Sep 12, 2026
FlowRAG: Synergizing Explicit Reasoning via Frequency-Aware Multi-Granularity Graph Flow
arXiv · Jun 17, 2026