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

2026-02-02

AI Summary

This work addresses the limitations of existing knowledge graph–based retrieval-augmented generation (RAG) methods, which rely on static graph structures and often fail to fully retrieve evidence chains in multi-hop queries due to semantic drift. To overcome this, the authors propose CatRAG, a framework built upon HippoRAG 2 that introduces a query-adaptive dynamic graph traversal mechanism. By integrating symbolic anchoring, query-aware dynamic edge weighting, and augmentation with key factual paragraphs, CatRAG transforms the static graph into a context-driven navigational structure. The approach combines personalized PageRank, symbolic constraints, and paragraph-level biasing to enable more complete multi-hop reasoning. Experimental results demonstrate that CatRAG substantially improves evidence chain recovery across four multi-hop benchmarks, achieving meaningful gains in reasoning completeness despite only modest improvements in standard recall metrics.

Technology Category

• Knowledge Representation and Reasoning: Common-Sense Reasoning
• Search and Optimization: Metareasoning and Metaheuristics
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

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 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.

Problem

• Retrieval-Augmented Generation
• Knowledge Graph
• multi-hop reasoning
• Static Graph Fallacy
• evidence retrieval

Innovation

• Context-Aware Traversal
• Dynamic Edge Weighting
• Symbolic Anchoring
• Retrieval-Augmented Generation
• Knowledge Graph