mlsanityData to 7 Oct 2026

PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths

arXiv 2502.14902 ↗First posted 18 Feb 2025cs.CL cs.AI cs.IRcited by 60

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

Retrieval-augmented generation (RAG) improves the response quality of large language models (LLMs) by retrieving knowledge from external databases. Typical RAG approaches split the text database into chunks, organizing them in a flat structure for efficient searches. To better capture the inherent dependencies and structured relationships across the text database, researchers propose to organize textual information into an indexing graph, known asgraph-based RAG. However, we argue that the limitation of current graph-based RAG methods lies in the redundancy of the retrieved information, rather than its insufficiency. Moreover, previous methods use a flat structure to organize retrieved information within the prompts, leading to suboptimal performance. To overcome these limitations, we propose PathRAG, which retrieves key relational paths from the indexing graph, and converts these paths into textual form for prompting LLMs. Specifically, PathRAG effectively reduces redundant information with flow-based pruning, while guiding LLMs to generate more logical and coherent responses with path-based prompting. Experimental results show that PathRAG consistently outperforms state-of-the-art baselines across six datasets and five evaluation dimensions. The code is available at the following link: https://github.com/BUPT-GAMMA/PathRAG

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 36 of its 57 references that are in the map. First posted on arXiv 18 Feb 2025.

Builds on

36 of 57 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation28 Oct
  2. 2024Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs14 Oct
  3. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning30 May
  4. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarization24 Apr

Other references · 32

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  5. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  6. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  7. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  8. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 724
  9. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  10. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
  11. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  12. 2023Large Language Models are Effective Text Rankers with Pairwise Ranking Promptingcited by 302
20 more
  1. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 275
  2. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 235
  3. 2020Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Basescited by 169
  4. 2019Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answeringcited by 147
  5. 2015Large-scale Simple Question Answering with Memory Networkscited by 127
  6. 2020KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoningcited by 106
  7. 2023Lift Yourself Up: Retrieval-augmented Text Generation with Self Memorycited by 103
  8. 2024Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Trainingcited by 88
  9. 2023Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrievalcited by 77
  10. 2024Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphscited by 77
  11. 2022FiD-Light: Efficient and Effective Retrieval-Augmented Text Generationcited by 63
  12. 2022Neuro-Symbolic Language Modeling with Automaton-augmented Retrievalcited by 60
  13. 2015Modeling Relation Paths for Representation Learning of Knowledge Basescited by 56
  14. 2022SQuALITY: Building a Long-Document Summarization Dataset the Hard Waycited by 50
  15. 2024The Chronicles of RAG: The Retriever, the Chunk and the Generatorcited by 34
  16. 2024HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMscited by 24
  17. 2024GraphInsight: Unlocking Insights in Large Language Models for Graph Structure Understandingcited by 18
  18. 2024ARL2: Aligning Retrievers for Black-box Large Language Models via Self-guided Adaptive Relevance Labelingcited by 10
  19. 2024Lost-in-Distance: Impact of Contextual Proximity on LLM Performance in Graph Taskscited by 8
  20. 2021Graph-augmented Learning to Rank for Querying Large-scale Knowledge Graphcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 17; 2026: 43.

60 papers.

Sort:

By area:

  1. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  2. 2025Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learningcited by 50
  3. 2025When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generationcited by 46
  4. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunitiescited by 23
  5. 2026HyperMem: Hypergraph Memory for Long-Term Conversationscited by 14
  6. 2025Cog-RAG: Cognitive-Inspired Dual-Hypergraph with Theme Alignment Retrieval-Augmented Generationcited by 9
  7. 2026AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rolloutscited by 8
  8. 2026SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented Executioncited by 8
  9. 2026Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guaranteescited by 7
  10. 2025Batch Query Processing and Optimization for Agentic Workflowscited by 6
  11. 2025Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generationcited by 3
  12. 2025GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generationcited by 3
38 more
  1. 2026HyperGraphPro: Progress-Aware Reinforcement Learning for Structure-Guided Hypergraph RAGcited by 3
  2. 2026S-Path-RAG: Semantic-Aware Shortest-Path Retrieval Augmented Generation for Multi-Hop Knowledge Graph Question Answeringcited by 3
  3. 2026Agents-K1: Towards Agent-native Knowledge Orchestrationcited by 3
  4. 2025PRoH: Dynamic Planning and Reasoning over Knowledge Hypergraphs for Retrieval-Augmented Generationcited by 2
  5. 2025NeuroPath: Neurobiology-Inspired Path Tracking and Reflection for Semantically Coherent Retrievalcited by 2
  6. 2026Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Modelscited by 2
  7. 2026RippleMem: From Isolated Retrieval to Associative Recollection for Long-Term Agent Memorycited by 2
  8. 2025TAdaRAG: Task Adaptive Retrieval-Augmented Generation via On-the-Fly Knowledge Graph Constructioncited by 1
  9. 2025Multi-hop Reasoning via Early Knowledge Alignmentcited by 1
  10. 2025TagRAG: Tag-guided Hierarchical Knowledge Graph Retrieval-Augmented Generationcited by 1
  11. 2026Toward Robust GraphRAG: Mitigating Retrieval Drift and Hallucination from Imperfect Knowledge Graphscited by 1
  12. 2026Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systemscited by 1
  13. 2026DOTRAG: Retrieval-Time Reasoning Along Pathscited by 1
  14. 2026AdaptR1: Reinforcement Learning Based Adaptive Interleaved Thinking in Multi-hop Question Answeringcited by 1
  15. 2026FLOWREADER: Min-Cost Flow Optimization for Multi-Modal Long Document Q&Acited by 1
  16. 2025ELITE: Embedding-Less retrieval with Iterative Text Explorationcited by 0
  17. 2025DGRAG: Distributed Graph-based Retrieval-Augmented Generation in Edge-Cloud Systemscited by 0
  18. 2025Graph-Guided Concept Selection for Efficient Retrieval-Augmented Generationcited by 0
  19. 2026A Navigational Approach for Comprehensive RAG via Traversal over Proposition Graphscited by 0
  20. 2026GraFine: Retrieval-Time Refinement for Efficient Graph RAG over Corpus Graphscited by 0
  21. 2026CE-GOCD: Central Entity-Guided Graph Optimization for Community Detection to Augment LLM Scientific Question Answeringcited by 0
  22. 2025C2-Cite: Contextual-Aware Citation Generation for Attributed Large Language Modelscited by 0
  23. 2026IGMiRAG: Intuition-Guided Retrieval-Augmented Generation with Adaptive Mining of In-Depth Memorycited by 0
  24. 2026SAGE: Structure Aware Graph Expansion for Retrieval of Heterogeneous Datacited by 0
  25. 2026Enhancing Scientific Literature Chatbots with Retrieval-Augmented Generation: A Performance Evaluation of Vector and Graph-Based Systemscited by 0
  26. 2026Condition-Gated Reasoning for Context-Dependent Biomedical Question Answeringcited by 0
  27. 2026AutothinkRAG: Complexity-Aware Control of Retrieval-Augmented Reasoning for Image-Text Interactioncited by 0
  28. 2026EvoRAG: Making Knowledge Graph-based RAG Automatically Evolve through Feedback-driven Backpropagationcited by 0
  29. 2026AstroVLM: Expert Multi-agent Collaborative Reasoning for Astronomical Imaging Quality Diagnosiscited by 0
  30. 2026Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generationcited by 0
  31. 2026ASTRA-QA: A Benchmark for Abstract Question Answering over Documentscited by 0
  32. 2026SeedER: Seed-Expand-Retrieve for Efficient Knowledge Graph Retrievalcited by 0
  33. 2026Generalized Rank-based Evaluation for Knowledge Graph Completion: Perspectives, Framework, and Analysescited by 0
  34. 2026LLMs+Graphs: Toward Graph-Native, Synergistic AI Systemscited by 0
  35. 2026Query-Aware Spreading Activation for Multi-Hop Retrieval over Knowledge Graphscited by 0
  36. 2026TRIAGE: Trustworthy Retrieval Instrumentation And Graph Evaluationcited by 0
  37. 2026GraphContainer: A Unified Platform for Comparing and Debugging Graph RAG Methodscited by 0
  38. 2026HyGRL: Adaptive Hybrid Graph Reasoning for Multi-Entity Questionscited by 0

50 most cited of 60 All 60 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Graph Retrieval-Augmented Generation: A Survey
  2. 2025NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes
  3. 2025RAG vs. GraphRAG: A Systematic Evaluation and Key Insights
  4. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey
  5. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)
  6. 2024LightRAG: Simple and Fast Retrieval-Augmented Generation
  7. 2025mmRAG: A Modular Benchmark for Retrieval-Augmented Generation over Text, Tables, and Knowledge Graphs
  8. 2025In-depth Analysis of Graph-based RAG in a Unified Framework