This repository contains a curated list of resources on graph-based retrieval-augmented generation (GraphRAG), which are classified according to "A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models". Continuously updating, stay tuned!

📃 Please cite our paper if you find our survey or repository helpful!

🎉 News

RAG vs. GraphRAG

GraphRAG is a new paradigm of RAG that revolutionizes domain-specific LLM applications, by addressing traditional RAG limitations through three key innovations: (i) graph-structured knowledge representation that explicitly captures entity relationships and domain hierarchies, (ii) graph-aware retrieval mechanisms that enable multi-hop reasoning and context-preserving knowledge acquisition, and (iii) structure-guided knowledge search algorithms that ensure efficient retrieval across large-scale corpora.

Comparison between traditional RAG and GraphRAG.

📫 Contact Us

We welcome researchers to share related work to enrich this list or provide insightful comments on our survey. Feel free to reach out to the corresponding co-first authors: Qinggang Zhang, Shengyuan Chen.

Table of Content

🍀 Citation
🍀 引用
📫 Contact Us
📫 联系我们
📈 Trend of GraphRAG Research
📈 GraphRAG 研究趋势
📜 Research Papers
• Knowledge Organization
  • Graph for Knowledge Indexing
  📜 研究论文 知识组织 用于知识索引的图
Graph as Knowledge Carrier
• Knowledge Graph Construction from Corpus
图作为知识载体 从语料库构建知识图谱
GraphRAG with Existing KGs
基于现有 KG 的 GraphRAG

(arXiv 2025) LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora [Paper]
(arXiv 2025) LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora [Paper]
(EMNLP 2025) Don’t Forget the Base Retriever! A Low-Resource Graph-based Retriever for Multi-hop Question Answering [Paper]
(EMNLP 2025) Don’t Forget the Base Retriever! A Low-Resource Graph-based Retriever for Multi-hop Question Answering [Paper]
(arXiv 2025) Query-Centric Graph Retrieval Augmented Generation [Paper]
(arXiv 2025) Query-Centric Graph Retrieval Augmented Generation [Paper]
(arXiv 2025) Multi-Agent GraphRAG: A Text-to-Cypher Framework for Labeled Property Graphs [Paper]
(arXiv 2025) Multi-Agent GraphRAG: A Text-to-Cypher Framework for Labeled Property Graphs [Paper]
(arXiv 2025) Grounded by Experience: Generative Healthcare Prediction Augmented with Hierarchical Agentic Retrieval [Paper]
(arXiv 2025) Grounded by Experience: Generative Healthcare Prediction Augmented with Hierarchical Agentic Retrieval [Paper]
(ICML 2025) HippoRAG2: From RAG to Memory: Non-Parametric Continual Learning for Large Language Models [Paper]
(ICML 2025) HippoRAG2: From RAG to Memory: Non-Parametric Continual Learning for Large Language Models [Paper]
(arXiv 2025) PersonaAgent with GraphRAG: Community-Aware Knowledge Graphs for Personalized LLM [Paper]
(arXiv 2025) PersonaAgent with GraphRAG: Community-Aware Knowledge Graphs for Personalized LLM [Paper]
(arXiv 2025) E^2GraphRAG: Streamlining Graph-based RAG for High Efficiency and Effectiveness [Paper]
(arXiv 2025) E^2GraphRAG: Streamlining Graph-based RAG for High Efficiency and Effectiveness [Paper]
(arXiv 2025) DIGIMON: A unified and modular graph-based RAG framework [Paper]
(arXiv 2025) DIGIMON: A unified and modular graph-based RAG framework [Paper]
(arXiv 2025) ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation [Paper]
(arXiv 2025) ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation [Paper]
(arXiv 2025) KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAG [Paper]
(arXiv 2025) KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAG [Paper]
(arXiv 2025) PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation [Paper]
(arXiv 2025) PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation [Paper]
(EMNLP 2025 Findings) Retrieval-Augmented Generation with Hierarchical Knowledge [Paper]
(EMNLP 2025 Findings) Retrieval-Augmented Generation with Hierarchical Knowledge [Paper]
• (arXiv 2024) Graph Neural Network Enhanced Retrieval for Question Answering of LLMs [Paper]
(arXiv 2024) KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation [Paper]
(arXiv 2024) KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation [Paper]
(arXiv 2024) OG-RAG: Ontology-Grounded Retrieval-Augmented Generation For Large Language Models [Paper]
(arXiv 2024) OG-RAG: Ontology-Grounded Retrieval-Augmented Generation For Large Language Models [Paper]
(arXiv 2024) GRAG: Graph Retrieval-Augmented Generation [Paper]
(arXiv 2024) GRAG: Graph Retrieval-Augmented Generation [Paper]
• (arXiv 2024) Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learning [Paper]
(ICLR 2024) RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval [Paper]
(ICLR 2024) RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval [Paper]
(AAAI 2024) Knowledge graph prompting for multi-document question answering [Paper]
(AAAI 2024) Knowledge graph prompting for multi-document question answering [Paper]
• (arXiv 2024) GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model [Paper]
(NeurIPS 2023) Avis: Autonomous visual information seeking with large language model agent [Paper]
(NeurIPS 2023) Avis: Autonomous visual information seeking with large language model agent [Paper]
(CoRL 2023) Sayplan: Grounding large language models using 3d scene graphs for scalable robot task planning [Paper]
(CoRL 2023) Sayplan: Grounding large language models using 3d scene graphs for scalable robot task planning [Paper]
(arXiv 2020) Answering complex open-domain questions with multi-hop dense retrieval [Paper]
(arXiv 2020) Answering complex open-domain questions with multi-hop dense retrieval [Paper]
(arXiv 2019) Knowledge guided text retrieval and reading for open domain question answering [Paper]
(arXiv 2019) Knowledge guided text retrieval and reading for open domain question answering [Paper]

• (AAAI 2026) You Don’t Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures [Paper]
(arXiv 2025) AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction [Paper]
(arXiv 2025) AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction [Paper]
(arXiv 2025) AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMs [Paper]
(arXiv 2025) AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMs [Paper]
(EMNLP 2025) MaGiX: A Multi-Granular Adaptive Graph Intelligence Framework for Enhancing Cross-Lingual RAG [Paper]
(EMNLP 2025) MaGiX: A Multi-Granular Adaptive Graph Intelligence Framework for Enhancing Cross-Lingual RAG [Paper]
(CIKM 2025) Context-Aware Fine-Grained Graph RAG for Query-Focused Summarization [Paper]
(CIKM 2025) Context-Aware Fine-Grained Graph RAG for Query-Focused Summarization [Paper]
(CIKM 2025) DocPolicyKG: A Lightweight LLM-Based Framework for Knowledge Graph Construction from Chinese Policy Documents [Paper]
(CIKM 2025) DocPolicyKG：一个基于轻量级LLM的框架，用于从中文政策文件中构建知识图谱 [Paper]
(arXiv 2025) SUBQRAG: SUB-QUESTION DRIVEN DYNAMIC GRAPH RAG [Paper]
(arXiv 2025) SUBQRAG：子问题驱动的动态图RAG (SUB-QUESTION DRIVEN DYNAMIC GRAPH RAG) [Paper]
(arXiv 2025) Ontology Learning and Knowledge Graph Construction: A Comparison of Approaches and Their Impact on RAG Performance [Paper]
(arXiv 2025) 本体学习与知识图谱构建：方法比较及其对RAG (Retrieval-Augmented Generation) 性能的影响 [Paper]
(NeurIPS 2025) GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation Paper
(NeurIPS 2025) GFM-RAG：用于检索增强生成 (Retrieval Augmented Generation) 的图基础模型 [Paper]
(arXiv 2025) G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge [Paper]
(arXiv 2025) G-reasoner：用于在图结构化知识上进行统一推理的基础模型 [Paper]
(CVPR 2025) Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation [Paper]
(CVPR 2025) 医学图RAG (Medical Graph RAG)：通过图检索增强生成 (Graph Retrieval-Augmented Generation) 实现安全医学大型语言模型 [Paper]
(arXiv 2025) Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning [Paper]
(arXiv 2025) Youtu-GraphRAG：用于图检索增强复杂推理 (Graph Retrieval-Augmented Complex Reasoning) 的垂直统一代理 [Paper]
(arXiv 2025) Retrieval-Augmented Generation with Hierarchical Knowledge [Paper]
(arXiv 2025) 具有分层知识的检索增强生成 (Retrieval-Augmented Generation) [Paper]
(arXiv 2025) MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilot [Paper]
(arXiv 2025) MedRAG：通过知识图谱引导的推理增强检索增强生成 (Retrieval-augmented Generation)，用于医疗保健副驾驶 [Paper]
(arXiv 2025) PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths [Paper]
(arXiv 2025) PathRAG：使用关系路径修剪基于图的检索增强生成 (Graph-based Retrieval Augmented Generation) [Paper]
(EDBT 2025) DBCopilot: Natural Language Querying over Massive Databases via Schema Routing [Paper]
(EDBT 2025) DBCopilot：通过模式路由对海量数据库进行自然语言查询 [Paper]
• (arXiv 2024) From local to global: A graph rag approach to query-focused summarization [Paper]
• (EMNLP 2024) Structure Guided Prompt: Instructing Large Language Model in Multi-Step Reasoning by Exploring Graph Structure of the Text [Paper]
(EMNLP 2024 Findings) GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models [Paper]
(EMNLP 2024 Findings) GraphReader：构建基于图的代理以增强大型语言模型的长上下文能力 [Paper]
(SIGIR 2024) Retrieval-augmented generation with knowledge graphs for customer service question answering [Paper]
(SIGIR 2024) 结合知识图谱的检索增强生成 (Retrieval-augmented generation)，用于客户服务问答 [Paper]
(arXiv 2024) DynaGRAG | Exploring the Topology of Information for Advancing Language Understanding and Generation in Graph Retrieval-Augmented Generation [Paper]
(arXiv 2024) DynaGRAG | 探索信息拓扑以推进图检索增强生成 (Graph Retrieval-Augmented Generation) 中的语言理解和生成 [Paper]
(arXiv 2024) FastRAG: Retrieval Augmented Generation for Semi-structured Data [Paper]
(arXiv 2024) FastRAG：用于半结构化数据的检索增强生成 (Retrieval Augmented Generation) [Paper]
(TechRxiv 2024) LuminiRAG: Vision-Enhanced Graph RAG for Complex Multi-Modal Document Understanding [Paper]
(TechRxiv 2024) LuminiRAG：用于复杂多模态文档理解的视觉增强图RAG (Vision-Enhanced Graph RAG) [Paper]
(BigData 2023) AutoKG: Efficient automated knowledge graph generation for language models [Paper]
(BigData 2023) AutoKG：用于语言模型的高效自动化知识图谱生成 [Paper]
(ACL 2019) Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs [Paper]
(ACL 2019) 使用本地知识图谱构建来将Seq2Seq模型扩展到多文档输入 [Paper]
(SIGIR 2019) Answering complex questions by joining multi-document evidence with quasi knowledge graphs [Paper]
(SIGIR 2019) 通过将多文档证据与准知识图谱连接起来回答复杂问题 [Paper]

(arXiv 2025) GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation [Paper]
(arXiv 2025) GraphSearch：用于图检索增强生成 (Graph Retrieval-Augmented Generation) 的Agentic深度搜索工作流程 [Paper]
(arXiv 2025) Detecting Hallucinations in Graph Retrieval-Augmented Generation via Attention Patterns and Semantic Alignment [Paper]
(arXiv 2025) 通过注意力模式和语义对齐检测图检索增强生成 (Graph Retrieval-Augmented Generation) 中的幻觉 [Paper]
（arXiv 2025） Inference Scaled GraphRAG: Improving Multi Hop Question Answering on Knowledge Graphs [Paper]
(arXiv 2025) Inference Scaled GraphRAG：改进知识图谱上的多跳问答 [Paper]
(AAAI 2025) LightPROF: A Lightweight Reasoning Framework for Large Language Model on Knowledge Graph [Paper]
(AAAI 2025) LightPROF：用于大型语言模型在知识图谱上进行推理的轻量级推理框架 [Paper]
(ICLR 2025) Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation [Paper]
(ICLR 2025) 简单有效：图和大型语言模型在基于知识图谱的检索增强生成 (Knowledge-Graph-Based Retrieval-Augmented Generation) 中的作用 [Paper]
(arXiv 2025) Empowering GraphRAG with Knowledge Filtering and Integration [Paper]
(arXiv 2025) 通过知识过滤和集成增强GraphRAG (GraphRAG) [Paper]
(arXiv 2024)StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization [Paper]
(arXiv 2024) StructRAG：通过推理时混合信息结构化 (Inference-time Hybrid Information Structurization) 增强LLM的知识密集型推理 [Paper]
• (ICLR 2024) Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning [Paper]
(AAAI 2024) Mitigating large language model hallucinations via autonomous knowledge graph-based retrofitting [Paper]
(AAAI 2024) 通过基于自主知识图谱的改造来减轻大型语言模型的幻觉 [Paper]
• (ICLR 2024) Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph [Paper]
(Bioinformatics 2024) Biomedical knowledge graph-enhanced prompt generation for large language models [Paper]
(Bioinformatics 2024) 用于大型语言模型的生物医学知识图谱增强提示生成 [Paper]
• (NeurIPS 2024) KnowGPT: Knowledge Graph based PrompTing for Large Language Models [Paper]
• (ACL 2024 Findings) Knowledge Graph-Enhanced Large Language Models via Path Selection [Paper]
(IEEE VIS 2024) KNOWNET: Guided Health Information Seeking from LLMs via Knowledge Graph Integration [Paper]
(IEEE VIS 2024) KNOWNET：通过知识图谱集成引导LLM的健康信息检索 [Paper]
(CoLM 2024) ProLLM: Protein Chain-of-Thoughts Enhanced LLM for Protein-Protein Interaction Prediction [Paper]
(CoLM 2024) ProLLM：用于蛋白质-蛋白质相互作用预测的蛋白质链式思考增强LLM (Protein Chain-of-Thoughts Enhanced LLM) [Paper]
(arXiv 2024) LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration [Paper]
(arXiv 2024) LEGO-GraphRAG：模块化基于图的检索增强生成 (Graph-based Retrieval-Augmented Generation)，用于设计空间探索 [Paper]
• (arXiv 2024) Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation [Paper]

(NAACL 2025) Knowledge Graph-Guided Retrieval Augmented Generation [Paper]
(NAACL 2025) 知识图谱引导的检索增强生成 (Knowledge Graph-Guided Retrieval Augmented Generation) [论文]
(ACL 2024 Findings) HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases[Paper]
(ACL 2024 Findings) HybGRAG：基于文本和关系知识库的混合检索增强生成 (Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases) [论文]
• (arXiv 2024) Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs [Paper]
(arXiv 2024) Medical graph rag: Towards safe medical large language model via graph retrieval-augmented generation [Paper]
(arXiv 2024) 医学图谱RAG：通过图检索增强生成实现安全的医学大型语言模型 (Medical graph rag: Towards safe medical large language model via graph retrieval-augmented generation) [论文]
(arXiv 2024) Codexgraph: Bridging large language models and code repositories via code graph databases [Paper]
(arXiv 2024) Codexgraph：通过代码图数据库连接大型语言模型和代码仓库 (Codexgraph: Bridging large language models and code repositories via code graph databases) [论文]

(AAAI 2024) StructuGraphRAG: Structured Document-Informed Knowledge Graphs for Retrieval-Augmented Generation [Paper]
(AAAI 2024) StructuGraphRAG：用于检索增强生成的结构化文档信息知识图谱 (Structured Document-Informed Knowledge Graphs for Retrieval-Augmented Generation) [论文]
(arXiv 2024) G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering [Paper]
(arXiv 2024) G-Retriever：用于文本图理解和问答的检索增强生成 (Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering) [论文]
(arXiv 2024) CancerKG.ORG A Web-scale, Interactive, Verifiable Knowledge Graph-LLM Hybrid for Assisting with Optimal Cancer Treatment and Care [Paper]
(arXiv 2024) CancerKG.ORG：一个网络规模的、交互式的、可验证的知识图谱-LLM混合系统，用于辅助最佳癌症治疗和护理 (A Web-scale, Interactive, Verifiable Knowledge Graph-LLM Hybrid for Assisting with Optimal Cancer Treatment and Care) [论文]
(arXiv 2024) Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learning [Paper]
(arXiv 2024) Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learning [Paper]
(arXiv 2024) GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model [Paper]
(arXiv 2024) GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model [Paper]
(arXiv 2024) Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation [Paper]
(arXiv 2024) 医学图谱RAG：通过图检索增强生成实现安全的医学大型语言模型 (Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation) [论文]
(arXiv 2024) How to Make LLMs Strong Node Classifiers? [Paper]
(arXiv 2024) 如何使LLM成为强大的节点分类器？ (How to Make LLMs Strong Node Classifiers?) [论文]

(AAAI 2026) You Don’t Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures [Paper]
(AAAI 2026) You Don’t Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures [Paper]
(NeurIPS 2024) KnowGPT: Knowledge Graph based PrompTing for Large Language Models [Paper]
(NeurIPS 2024) KnowGPT：基于知识图谱的提示 (Knowledge Graph based PrompTing)，用于大型语言模型 [Paper]
• (ACL 2024 Findings) Knowledge Graph-Enhanced Large Language Models via Path Selection [Paper]
• (ICLR 2024) Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph [Paper]
(CIKM 2024) RD-P: A Trustworthy Retrieval-Augmented Prompter with Knowledge Graphs for LLMs [Paper]
(CIKM 2024) RD-P：一个值得信赖的检索增强提示器，具有知识图谱，用于LLM (A Trustworthy Retrieval-Augmented Prompter with Knowledge Graphs for LLMs) [论文]
(arXiv 2024) RuleRAG: Rule-Guided Retrieval-Augmented Generation with Language Models for Question Answering [Paper]
(arXiv 2024) RuleRAG：使用语言模型进行问题解答的规则引导的检索增强生成 (Rule-Guided Retrieval-Augmented Generation with Language Models for Question Answering) [论文]
(LHB 2024) Intelligent question answering for water conservancy project inspection driven by knowledge graph and large language model collaboration [Paper]
(LHB 2024) 知识图谱和大型语言模型协同驱动的水利工程智能问答 (Intelligent question answering for water conservancy project inspection driven by knowledge graph and large language model collaboration) [论文]
(arXiv 2024) RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs [Paper]
(arXiv 2024) RiTeK：一个用于大型语言模型对文本知识图谱进行复杂推理的数据集 (A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs) [论文]

(AAAI 2024) Knowledge graph prompting for multi-document question answering [Paper]
(AAAI 2024) 用于多文档问答的知识图谱提示 (Knowledge graph prompting for multi-document question answering) [论文]
(EMNLP 2024) Structure Guided Prompt: Instructing Large Language Model in Multi-Step Reasoning by Exploring Graph Structure of the Text [Paper]
(EMNLP 2024) 结构引导提示：通过探索文本的图结构来指导大型语言模型进行多步推理 [Paper]
(ACML 2024) Enhancing Textbook Question Answering with Knowledge Graph-Augmented Large Language Models [Paper]
(ACML 2024) 使用知识图谱增强的大型语言模型增强教科书问答 (Enhancing Textbook Question Answering with Knowledge Graph-Augmented Large Language Models) [论文]
(ICLR 2024) Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph [Paper]
(ICLR 2024) Think-on-Graph：大型语言模型在知识图谱上的深度和负责任的推理 (Deep and Responsible Reasoning of Large Language Model on Knowledge Graph) [论文]
(arXiv 2024) LightRAG: Simple and Fast Retrieval-Augmented Generation [Paper]
(arXiv 2024) LightRAG：简单快速的检索增强生成 (Simple and Fast Retrieval-Augmented Generation) [论文]
(arXiv 2024) MEG: Medical Knowledge-Augmented Large Language Models for Question Answering [Paper]
(arXiv 2024) MEG：用于问答的医学知识增强大型语言模型 (Medical Knowledge-Augmented Large Language Models for Question Answering) [论文]
(arXiv 2024) From local to global: A graph rag approach to query-focused summarization [Paper]
(arXiv 2024) 从局部到全局：一种用于查询聚焦摘要的图RAG (graph RAG) 方法 [Paper]

(arXiv 2025) CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMs [Paper]
(arXiv 2025) CG-RAG：通过引用图检索增强LLM进行研究问题解答 (Research Question Answering by Citation Graph Retrieval-Augmented LLMs) [论文]
(arXiv 2024) Advanced RAG Models with Graph Structures: Optimizing Complex Knowledge Reasoning and Text Generation [Paper]
(arXiv 2024) 具有图结构的高级RAG模型：优化复杂知识推理和文本生成 (Advanced RAG Models with Graph Structures: Optimizing Complex Knowledge Reasoning and Text Generation) [论文]
(arXiv 2024) Language Models are Graph Learners [Paper]
(arXiv 2024) 语言模型是图学习器 (Language Models are Graph Learners) [论文]
(arXiv 2024) Graph Neural Network Enhanced Retrieval for Question Answering of LLMs [Paper]
(arXiv 2024) Graph Neural Network Enhanced Retrieval for Question Answering of LLMs [Paper]
(arXiv 2024) Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation [Paper]
(arXiv 2024) 用于知识基础对话生成的知识图谱增强语言模型 (Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation) [论文]

• (arXiv 2024) Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs [Paper]
(arXiv 2024) Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog Generation [Paper]
(arXiv 2024) 用于知识图谱基础的对话生成的生成式子图检索 (Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog Generation) [论文]
(arXiv 2024) Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs [Paper]
(arXiv 2024) 记录图：通过图结构增强检索增强生成以实现长文本摘要 (Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs) [论文]

(ACL 2024) Boosting Language Models Reasoning with Chain-of-Knowledge Prompting [Paper]
(ACL 2024) 通过知识链提示（Chain-of-Knowledge Prompting）提升语言模型推理能力[论文]
(ACL 2024 Findings) Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments [Paper]
(ACL 2024 Findings) 有需要再联系我：LLM可以高效且忠实地推理结构化环境（Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments）[论文]
(arXiv 2024) Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models [Paper]
(arXiv 2024) 图约束推理：利用大型语言模型对知识图谱进行忠实推理（Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models）[论文]
(arXiv 2024) Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofitting [Paper]
(arXiv 2024) 通过基于自主知识图谱的改造来减轻大型语言模型的幻觉（Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofitting）[论文]

• (arXiv 2024) Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation [Paper]
(arXiv 2024) StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization [Paper]
(arXiv 2024) StructRAG：通过推理时混合信息结构化来提升LLM的知识密集型推理（StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization）[论文]

(arXiv 2025) Large Language Models based Graph Convolution for Text-Attributed Networks? [Paper]
(arXiv 2025) 基于大型语言模型的图卷积用于文本属性网络？（Large Language Models based Graph Convolution for Text-Attributed Networks?）[论文]
(SIGIR 2024) Graphgpt: Graph instruction tuning for large language models [Paper]
(SIGIR 2024) GraphGPT：用于大型语言模型的图指令调优（Graphgpt: Graph instruction tuning for large language models）[论文]

(AAAI 2024) Exploring large language model for graph data understanding in online job recommendations [Paper]
(AAAI 2024) 探索大型语言模型在在线职位推荐中对图数据理解的应用（Exploring large language model for graph data understanding in online job recommendations）[论文]
(arXiv 2024) MuseGraph: Graph-oriented Instruction Tuning of Large Language Models for Generic Graph Mining [Paper]
(arXiv 2024) MuseGraph：面向图的大型语言模型指令调优，用于通用图挖掘（MuseGraph: Graph-oriented Instruction Tuning of Large Language Models for Generic Graph Mining）[论文]
(WWW 2023) Structure pretraining and prompt tuning for knowledge graph transfer [Paper]
(WWW 2023) 知识图谱迁移的结构预训练和提示调优（Structure pretraining and prompt tuning for knowledge graph transfer）[论文]
(ICLR 2023) Reasoning on graphs: Faithful and interpretable large language model reasoning [Paper]
(ICLR 2023) 图上的推理：忠实且可解释的大型语言模型推理（Reasoning on graphs: Faithful and interpretable large language model reasoning）[论文]

(ICML 2024) Llaga: Large language and graph assistant [Paper]
(ICML 2024) Llaga：大型语言和图助手（Llaga: Large language and graph assistant）[论文]
(KDD 2024) Graphwiz: An instruction-following language model for graph problems [Paper]
(KDD 2024) GraphWiz：用于图问题的指令跟随语言模型（Graphwiz: An instruction-following language model for graph problems）[论文]
(AAAI 2024) Graph neural prompting with large language models [Paper]
(AAAI 2024) 使用大型语言模型的图神经提示（Graph neural prompting with large language models）[论文]
(ACL 2024 Findings) Rho:Reducing hallucination in open-domain dialogues with knowledge grounding [Paper]
(ACL 2024 Findings) Rho：通过知识基础减少开放领域对话中的幻觉（Rho:Reducing hallucination in open-domain dialogues with knowledge grounding）[论文]
(EACL 2024 Findings) Language is All a Graph Needs [Paper]
(EACL 2024 Findings) 语言是图所需的一切（Language is All a Graph Needs）[论文]

(KBS 2025) Different paths to the same destination: Diversifying LLMs generation for multi-hop open-domain question answering [Paper]
(KBS 2025) 通往同一目的地的不同路径：多样化LLM生成，用于多跳开放领域问答（Different paths to the same destination: Diversifying LLMs generation for multi-hop open-domain question answering）[论文]
(ICLR 2024) Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning [Paper]
(ICLR 2024) 图上推理：大型语言模型的可信和可解释的推理 [Paper]
(ICLR 2024) Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph [Paper]
(ICLR 2024) Think-on-Graph：大型语言模型在知识图谱上的深度和负责任的推理 [Paper]
(arXiv 2024) Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation [Paper]
(arXiv 2024) Think-on-Graph 2.0：基于知识引导的检索增强生成 (Knowledge-guided Retrieval Augmented Generation) 的大型语言模型的深度和可信推理 [Paper]
(arXiv 2024) Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs [Paper]
(arXiv 2024) 图思维链：通过在图上推理来增强大型语言模型 (Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs) [论文]
(ICLR 2024) Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources [Paper]
(ICLR 2024) 知识链：通过异构来源上的动态知识适应来支持大型语言模型（Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources）[论文]
(ACL 2024 Findings) Visual In-Context Learning for Large Vision-Language Models [Paper]
(ACL 2024 Findings) 用于大型视觉语言模型的视觉上下文学习（Visual In-Context Learning for Large Vision-Language Models）[论文]
(NeurIPS 2023) What makes good examples for visual in-context learning? [Paper]
(NeurIPS 2023) 什么构成了视觉上下文学习的好例子？（What makes good examples for visual in-context learning?）[论文]
(ACL 2023) Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models [Paper]
(ACL 2023) 计划和解决提示：通过大型语言模型改进零样本思维链推理（Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models）[论文]
(AAAI 2024) When Do Program-of-Thought Works for Reasoning? [Paper]
(AAAI 2024) 程序思维何时适用于推理？（When Do Program-of-Thought Works for Reasoning?）[论文]
(ICLR 2022) An Explanation of In-context Learning as Implicit Bayesian Inference [Paper]
(ICLR 2022) 作为隐式贝叶斯推理的上下文学习解释（An Explanation of In-context Learning as Implicit Bayesian Inference）[论文]
(EMNLP 2023) KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Bases [Paper]
(EMNLP 2023) KnowledGPT：通过对知识库的检索和存储访问来增强大型语言模型（KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Bases）[论文]

(AAAI 2024) Mitigating large language model hallucinations via autonomous knowledge graph-based retrofitting [Paper]
(AAAI 2024) 通过基于知识图谱的自主改造来缓解大型语言模型幻觉 (Mitigating large language model hallucinations via autonomous knowledge graph-based retrofitting) [论文 (Paper)]
(ACL 2024 Findings) Knowledge Graph-Enhanced Large Language Models via Path Selection [Paper]
(ACL 2024 Findings) 通过路径选择的知识图谱增强大型语言模型 [Paper]
(NeurIPS 2024) Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs [Paper]
(NeurIPS 2024) 图上规划：基于知识图谱的大型语言模型自校正自适应规划 (Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs) [论文 (Paper)]
(arXiv 2024) Explore then Determine: A GNN-LLM Synergy Framework for Reasoning over Knowledge Graph [Paper]
(arXiv 2024) 先探索后确定：用于知识图谱推理的 GNN-LLM 协同框架 (Explore then Determine: A GNN-LLM Synergy Framework for Reasoning over Knowledge Graph) [论文 (Paper)]
(ACL 2024) CogMG: Collaborative Augmentation Between Large Language Model and Knowledge Graph [Paper]
(ACL 2024) CogMG：大型语言模型和知识图谱之间的协同增强 (CogMG: Collaborative Augmentation Between Large Language Model and Knowledge Graph) [论文 (Paper)]

(arXiv 2025) Retrieval-Augmented Generation with Graphs (GraphRAG) [Paper]
(arXiv 2025) 基于图的检索增强生成 (GraphRAG (Retrieval-Augmented Generation with Graphs)) [论文 (Paper)]
(arXiv 2024) Graph Retrieval-Augmented Generation: A Survey [Paper]
(arXiv 2024) 图检索增强生成：一项调查 (Graph Retrieval-Augmented Generation: A Survey) [论文 (Paper)]
(AIxSET 2024) Graph Retrieval-Augmented Generation for Large Language Models: A Survey [Paper]
(AIxSET 2024) 用于大型语言模型的图检索增强生成：一项调查 (Graph Retrieval-Augmented Generation for Large Language Models: A Survey) [论文 (Paper)]

Awesome-LLMs-in-Graph-tasks by Yuhan Li from HKUST(GZ).
香港科技大学（广州）李雨涵的 Awesome-LLMs-in-Graph-tasks。
Awesome-Graph-LLM by Xiaoxin He from NUS.
新加坡国立大学何晓新的 Awesome-Graph-LLM。
Awesome-Graph-Prompt, created by Xixi Wu from CUHK.
香港中文大学吴希希创建的 Awesome-Graph-Prompt。

Semantica: an open-source, production-ready semantic layer and GraphRAG framework that sits between raw corpora and LLMs.
Semantica：一个开源的、生产就绪的语义层和 GraphRAG (GraphRAG) 框架，位于原始语料库和 LLM (LLMs) 之间。
Graph RAG pipeline that runs locally with ollama and has full source attribution
使用 ollama 在本地运行并具有完整来源归属的图 RAG (Graph RAG) 管道。
GraphRAG-Bench: A Comprehensive Benchmark and Analysis for Graph Retrieval-Augmented Generation.
GraphRAG-Bench：一个用于图检索增强生成 (Graph Retrieval-Augmented Generation) 的综合基准测试和分析。
Agentic-RAG: A clean and extensible agentic RAG system.
Agentic-RAG：一个干净且可扩展的 agentic RAG (agentic RAG) 系统。
ApeRAG: Production-ready GraphRAG with multi-modal indexing, AI agents, MCP support, and scalable K8s deployment
ApeRAG：生产就绪的 GraphRAG (GraphRAG)，具有多模态索引、AI 代理、MCP (MCP) 支持和可扩展的 K8s (K8s) 部署
Graphiti: Build Real-Time Knowledge Graphs for AI Agents.
Graphiti：为 AI 代理构建实时知识图谱 (Real-Time Knowledge Graphs)。
DIGIMON: A unified and modular graph-based RAG framework
DIGIMON：一个统一且模块化的基于图的 RAG (RAG) 框架
Microsoft-GraphRAG: A modular graph-based Retrieval-Augmented Generation (RAG) system
Microsoft-GraphRAG：一个模块化的基于图的检索增强生成 (Retrieval-Augmented Generation (RAG)) 系统
Nano-GraphRAG: A simple, easy-to-hack GraphRAG implementation
Nano-GraphRAG：一个简单、易于修改的 GraphRAG (GraphRAG) 实现
Fast GraphRAG: RAG that intelligently adapts to your use case, data, and queries
Fast GraphRAG：智能地适应您的用例、数据和查询的 RAG (RAG)
LightRAG: Simple and Fast Retrieval-Augmented Generation
LightRAG：简单快速的检索增强生成 (Retrieval-Augmented Generation)
HuixiangDou2: A Robustly Optimized GraphRAG Approach
HuixiangDou2：一种稳健优化的 GraphRAG (GraphRAG) 方法
GraphRAG-SDK: a specialized toolkit for building GraphRAG systems.
GraphRAG-SDK：一个用于构建 GraphRAG (GraphRAG) 系统的专用工具包。
Code-Graph-RAG: A graph-based RAG system that analyzes multi-language codebases using Tree-sitter, builds knowledge graphs, and enables natural language querying and editing via MCP server.
Code-Graph-RAG：一个基于图的 RAG (RAG) 系统，它使用 Tree-sitter 分析多语言代码库，构建知识图谱，并通过 MCP (MCP) 服务器实现自然语言查询和编辑。
WFGY Problem Map: a specialized toolkit that defines 16 recurring failure modes that show up in RAG and LLM pipelines.
WFGY 问题地图：一个专门的工具包，定义了 16 种 RAG (RAG) 和 LLM (LLM) 管道中反复出现的失效模式。

@article{zhang2025survey,
  title={A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models},
  author={Zhang, Qinggang and Chen, Shengyuan and Bei, Yuanchen and Yuan, Zheng and Zhou, Huachi and Hong, Zijin and Dong, Junnan and Chen, Hao and Chang, Yi and Huang, Xiao},
  journal={arXiv preprint arXiv:2501.13958},
  year={2025}
}