mlsanityData to 7 Oct 2026

Graph Retrieval-Augmented Generation: A Survey

arXiv 2408.08921 ↗First posted 15 Aug 2024cs.AI cs.CL cs.IRcited by 320

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

Abstract (arXiv)

Recently, Retrieval-Augmented Generation (RAG) has achieved remarkable success in addressing the challenges of Large Language Models (LLMs) without necessitating retraining. By referencing an external knowledge base, RAG refines LLM outputs, effectively mitigating issues such as ``hallucination'', lack of domain-specific knowledge, and outdated information. However, the complex structure of relationships among different entities in databases presents challenges for RAG systems. In response, GraphRAG leverages structural information across entities to enable more precise and comprehensive retrieval, capturing relational knowledge and facilitating more accurate, context-aware responses. Given the novelty and potential of GraphRAG, a systematic review of current technologies is imperative. This paper provides the first comprehensive overview of GraphRAG methodologies. We formalize the GraphRAG workflow, encompassing Graph-Based Indexing, Graph-Guided Retrieval, and Graph-Enhanced Generation. We then outline the core technologies and training methods at each stage. Additionally, we examine downstream tasks, application domains, evaluation methodologies, and industrial use cases of GraphRAG. Finally, we explore future research directions to inspire further inquiries and advance progress in the field. In order to track recent progress in this field, we set up a repository at urlhttps://github.com/pengboci/GraphRAG-Survey.

Key facts. Cited by 320 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 127 of its 198 references that are in the map. First posted on arXiv 15 Aug 2024.

Builds on

127 of 198 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning30 May
  2. 2024Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answering26 Apr
  3. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarization24 Apr
  4. 2023ATLANTIC: Structure-Aware Retrieval-Augmented Language Model for Interdisciplinary Science21 Nov
  5. 2023FABULA: Intelligence Report Generation Using Retrieval-Augmented Narrative Construction20 Oct

Other references · 122

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2022Training language models to follow instructions with human feedbackcited by 15,712
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  6. 2024The Llama 3 Herd of Modelscited by 14,192
  7. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  8. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  9. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  10. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  11. 2017Graph Attention Networkscited by 8,854
  12. 2017Inductive Representation Learning on Large Graphscited by 6,284
38 more
  1. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  5. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  6. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  7. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,818
  8. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  9. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,114
  10. 2024Qwen2 Technical Reportcited by 2,076
  11. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  12. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,324
  13. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  14. 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
  15. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  16. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  17. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
  18. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  19. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
  20. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  21. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  22. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  23. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 326
  24. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
  25. 2023Exploring the Potential of Large Language Models (LLMs) in Learning on Graphscited by 271
  26. 2020COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphscited by 254
  27. 2023Can Language Models Solve Graph Problems in Natural Language?cited by 249
  28. 2016Key-Value Memory Networks for Directly Reading Documentscited by 223
  29. 2023Large Language Models in Finance: A Surveycited by 223
  30. 2023Language is All a Graph Needscited by 219
  31. 2019KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoningcited by 216
  32. 2023GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarkingcited by 209
  33. 2023Large Language Models on Graphs: A Comprehensive Surveycited by 190
  34. 2024Large Language Models for Education: A Survey and Outlookcited by 185
  35. 2019PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Textcited by 182
  36. 2024LLaGA: Large Language and Graph Assistantcited by 177
  37. 2017Variational Reasoning for Question Answering with Knowledge Graphcited by 170
  38. 2020Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Basescited by 169

50 most cited of 122 All 122 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 23; 2025: 161; 2026: 136.

320 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 285
  2. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  3. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 85
  4. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generationcited by 78
  5. 2024KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generationcited by 67
  6. 2024GraphCLIP: Enhancing Transferability in Graph Foundation Models for Text-Attributed Graphscited by 58
  7. 2025RAG vs. GraphRAG: A Systematic Evaluation and Key Insightscited by 51
  8. 2025Retrieval-Augmented Generation with Hierarchical Knowledgecited by 46
  9. 2025When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generationcited by 46
  10. 2025In-depth Analysis of Graph-based RAG in a Unified Frameworkcited by 45
  11. 2025GFM-RAG: Graph Foundation Model for Retrieval Augmented Generationcited by 40
  12. 2025Parametric Retrieval Augmented Generationcited by 38
38 more
  1. 2025Position: Episodic Memory is the Missing Piece for Long-Term LLM Agentscited by 35
  2. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 34
  3. 2025Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunitiescited by 30
  4. 2025KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAGcited by 29
  5. 2025AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answeringcited by 29
  6. 2025RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defectscited by 27
  7. 2025ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generationcited by 27
  8. 2024HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Basescited by 26
  9. 2025G-Refer: Graph Retrieval-Augmented Large Language Model for Explainable Recommendationcited by 26
  10. 2024MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistantscited by 24
  11. 2024Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrievalcited by 24
  12. 2025GraphRAG-Bench: Challenging Domain-Specific Reasoning for Evaluating Graph Retrieval-Augmented Generationcited by 24
  13. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunitiescited by 23
  14. 2025You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structurescited by 23
  15. 2025Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoningcited by 22
  16. 2025MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversationscited by 21
  17. 2025WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Modelscited by 18
  18. 2025GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environmentscited by 18
  19. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Surveycited by 18
  20. 2025RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarkingcited by 17
  21. 2025Optimizing the Interface Between Knowledge Graphs and LLMs for Complex Reasoningcited by 17
  22. 2025MMGraphRAG: Bridging Vision and Language with Interpretable Multimodal Knowledge Graphscited by 16
  23. 2025Explicit v.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized Informationcited by 16
  24. 2025BookRAG: A Hierarchical Structure-aware Index-based Approach for Retrieval-Augmented Generation on Complex Documentscited by 16
  25. 2025Graph RAG-Tool Fusioncited by 15
  26. 2025Tool-to-Agent Retrieval: Bridging Tools and Agents for Scalable LLM Multi-Agent Systemscited by 15
  27. 2025CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Executioncited by 14
  28. 2025EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corporacited by 14
  29. 2025Graph World Modelcited by 14
  30. 2025LeanRAG: Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical Retrievalcited by 14
  31. 2024CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Eracited by 13
  32. 2025Knowledge Graph-based Retrieval-Augmented Generation for Schema Matchingcited by 13
  33. 2025AssertionForge: Enhancing Formal Verification Assertion Generation with Structured Representation of Specifications and RTLcited by 13
  34. 2024KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Modelscited by 12
  35. 2025KiRAG: Knowledge-Driven Iterative Retriever for Enhancing Retrieval-Augmented Generationcited by 12
  36. 2025GraphRAG-R1: Graph Retrieval-Augmented Generation with Process-Constrained Reinforcement Learningcited by 12
  37. 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Frameworkcited by 12
  38. 2024Can LLMs be Good Graph Judge for Knowledge Graph Construction?cited by 11

50 most cited of 320 All 320 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes
  2. 2025MiniRAG: Towards Extremely Simple Retrieval-Augmented Generation
  3. 2024LightRAG: Simple and Fast Retrieval-Augmented Generation
  4. 2025LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora
  5. 2025PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths
  6. 2025mmRAG: A Modular Benchmark for Retrieval-Augmented Generation over Text, Tables, and Knowledge Graphs
  7. 2025Pseudo-Knowledge Graph: Meta-Path Guided Retrieval and In-Graph Text for RAG-Equipped LLM
  8. 2025Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG