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

• URL: http://arxiv.org/abs/2602.01965v1
• Date: Mon, 02 Feb 2026 11:13:38 GMT
• Title: Breaking the Static Graph: Context-Aware Traversal for Robust Retrieval-Augmented Generation
• Authors: Kwun Hang Lau, Fangyuan Zhang, Boyu Ruan, Yingli Zhou, Qintian Guo, Ruiyuan Zhang, Xiaofang Zhou,
• Abstract summary: We propose CatRAG, Context-Aware Traversal for robust RAG.<n>CatRAG builds on the HippoRAG 2 architecture and transforms the static KG into a query-adaptive navigation structure.<n> Experiments across four multi-hop benchmarks demonstrate that CatRAG consistently outperforms state of the art baselines.
• Score: 12.71443292660797
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• HELP: HyperNode Expansion and Logical Path-Guided Evidence Localization for Accurate and Efficient GraphRAG [53.30561659838455]
  Large Language Models (LLMs) often struggle with inherent knowledge boundaries and hallucinations.<n>Retrieval-Augmented Generation (RAG) frequently overlooks structural interdependencies essential for multi-hop reasoning.<n>Help achieves competitive performance across multiple simple and multi-hop QA benchmarks and up to a 28.8$times$ speedup over leading Graph-based RAG baselines.
  arXiv  Detail & Related papers  (2026-02-24T14:05:29Z)
• HyperRAG: Reasoning N-ary Facts over Hypergraphs for Retrieval Augmented Generation [22.189132611244105]
  HyperRAG is a RAG framework tailored for n-ary hypergraphs.<n>It learns structural-semantic reasoning over n-ary facts to construct query-conditioned relational chains.<n>It achieves the highest answer accuracy overall, with average gains of 2.95% in MRR and 1.23% in Hits@10 over the strongest baseline.
  arXiv  Detail & Related papers  (2026-02-16T05:15:55Z)
• CoG: Controllable Graph Reasoning via Relational Blueprints and Failure-Aware Refinement over Knowledge Graphs [53.199517625701475]
  CoG is a training-free framework inspired by Dual-Process Theory that mimics the interplay between intuition and deliberation.<n>CoG significantly outperforms state-of-the-art approaches in both accuracy and efficiency.
  arXiv  Detail & Related papers  (2026-01-16T07:27:40Z)
• PruneRAG: Confidence-Guided Query Decomposition Trees for Efficient Retrieval-Augmented Generation [19.832367438725306]
  PruneRAG builds a structured query decomposition tree to perform stable and efficient reasoning.<n>We define the Evidence Forgetting Rate as a metric to quantify cases where golden evidence is retrieved but not correctly used.
  arXiv  Detail & Related papers  (2026-01-16T06:38:17Z)
• Relink: Constructing Query-Driven Evidence Graph On-the-Fly for GraphRAG [10.60635000782353]
  We argue for a textitreason-and-construct paradigm and propose Relink, a framework that dynamically builds a query-specific evidence graph.<n>Relink achieves significant average improvements of 5.4% in EM and 5.2% in F1 over leading GraphRAG baselines.
  arXiv  Detail & Related papers  (2026-01-12T04:35:23Z)
• A Navigational Approach for Comprehensive RAG via Traversal over Proposition Graphs [23.840376380790783]
  ToPG models its knowledge base as a heterogeneous graph of propositions, entities, and passages.<n>ToPG demonstrates strong performance across both accuracy- and quality-based metrics.
  arXiv  Detail & Related papers  (2026-01-08T11:50:40Z)
• TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework [62.66056331998838]
  TeaRAG is a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps.<n>Our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps.
  arXiv  Detail & Related papers  (2025-11-07T16:08:34Z)
• Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG [40.27922416050001]
  Graph-based RAG (GraphRAG) is a powerful paradigm for improving large language models (LLMs) on knowledge-intensive question answering.<n>Iterative retrieval has emerged as a promising alternative, yet its role within GraphRAG remains poorly understood.<n>We present the first systematic study of iterative retrieval in GraphRAG, analyzing how different strategies interact with graph-based backbones.
  arXiv  Detail & Related papers  (2025-09-29T21:38:28Z)
• Respecting Temporal-Causal Consistency: Entity-Event Knowledge Graphs for Retrieval-Augmented Generation [69.45495166424642]
  We develop a robust and discriminative QA benchmark to measure temporal, causal, and character consistency understanding in narrative documents.<n>We then introduce Entity-Event RAG (E2RAG), a dual-graph framework that keeps separate entity and event subgraphs linked by a bipartite mapping.<n>Across ChronoQA, our approach outperforms state-of-the-art unstructured and KG-based RAG baselines, with notable gains on causal and character consistency queries.
  arXiv  Detail & Related papers  (2025-06-06T10:07:21Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)
• Chain-of-Retrieval Augmented Generation [91.02950964802454]
  This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer.<n>Our proposed method, CoRAG, allows the model to dynamically reformulate the query based on the evolving state.
  arXiv  Detail & Related papers  (2025-01-24T09:12:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.