Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Breaking the Static Graph: Context-Aware Traversal for Robust Retrieval-Augmented Generation

About

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 navigation structure. We introduce a multi-faceted framework to steer the random walk: (1) Symbolic Anchoring, which injects weak entity constraints to regularize the random walk; (2) Query-Aware Dynamic Edge Weighting, which dynamically modulates graph structure, to prune irrelevant paths while amplifying those aligned with the query's intent; and (3) Key-Fact Passage Weight Enhancement, a cost-efficient bias that structurally anchors the random walk to likely evidence. Experiments across four multi-hop benchmarks demonstrate that CatRAG consistently outperforms state of the art baselines. Our analysis reveals that while standard Recall metrics show modest gains, CatRAG achieves substantial improvements in reasoning completeness, the capacity to recover the entire evidence path without gaps. These results reveal that our approach effectively bridges the gap between retrieving partial context and enabling fully grounded reasoning. Resources are available at https://github.com/kwunhang/CatRAG.

Kwun Hang Lau, Fangyuan Zhang, Boyu Ruan, Yingli Zhou, Qintian Guo, Ruiyuan Zhang, Xiaofang Zhou• 2026

Related benchmarks

TaskDatasetResultRank
Multi-hop Question AnsweringHotpotQA (test)
F171.4
198
Multi-hop Question AnsweringMuSiQue (test)
F145
111
RetrievalHotpotQA
R@589.5
24
Multi-hop Question Answering2Wiki (test)
F1 Score69.7
20
Multi-hop Question AnsweringMuSiQue
FCR34.6
7
Multi-hop Question Answering2Wiki
FCR67.6
7
Multi-hop Question AnsweringHotpotQA
FCR80.4
7
Retrieval2Wiki
Recall@587
7
RetrievalHOVER
Recall@50.768
7
Showing 9 of 9 rows

Other info

Follow for update