Breaking the Static Graph: Context-Aware Traversal for Robust Retrieval-Augmented Generation
Kwun Hang Lau, Fangyuan Zhang, Boyu Ruan, Yingli Zhou, Qintian Guo, Ruiyuan Zhang, Xiaofang Zhou

TL;DR
This paper introduces CatRAG, a novel framework for retrieval-augmented generation that dynamically adapts graph traversal to query context, significantly improving multi-hop reasoning and evidence retrieval over static graph methods.
Contribution
We propose CatRAG, a query-adaptive graph traversal framework that enhances knowledge graph navigation for robust multi-hop reasoning in RAG systems.
Findings
Outperforms state-of-the-art baselines on four multi-hop benchmarks.
Achieves substantial improvements in reasoning completeness and evidence retrieval.
Effectively bridges the gap between partial retrieval and full evidence chain recovery.
Abstract
Recent advances in Retrieval-Augmented Generation (RAG) have shifted from simple vector similarity to structure-aware approaches like HippoRAG, which leverage Knowledge Graphs (KGs) and Personalized PageRank (PPR) to capture multi-hop dependencies. However, these methods suffer from a "Static Graph Fallacy": they rely on fixed transition probabilities determined during indexing. This rigidity ignores the query-dependent nature of edge relevance, causing semantic drift where random walks are diverted into high-degree "hub" nodes before reaching critical downstream evidence. Consequently, models often achieve high partial recall but fail to retrieve the complete evidence chain required for multi-hop queries. To address this, we propose CatRAG, Context-Aware Traversal for robust RAG, a framework that builds on the HippoRAG 2 architecture and transforms the static KG into a query-adaptive…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Graph Neural Networks · Information Retrieval and Search Behavior · Topic Modeling
