mlsanityData to 7 Oct 2026

Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval

arXiv 2604.15951 ↗First posted 17 Apr 2026cs.AIcited by 1

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 1 more
Abstract (arXiv)

Generative AI, particularly Large Language Models, increasingly integrates graph-based representations to enhance reasoning, retrieval, and structured decision-making. Despite rapid advances, there remains limited clarity regarding when, why, where, and what types of graph-LLM integrations are most appropriate across applications. This survey provides a concise, structured overview of the design choices underlying the integration of graphs with LLMs. We categorize existing methods based on their purpose (reasoning, retrieval, generation, recommendation), graph modality (knowledge graphs, scene graphs, interaction graphs, causal graphs, dependency graphs), and integration strategies (prompting, augmentation, training, or agent-based use). By mapping representative works across domains such as cybersecurity, healthcare, materials science, finance, robotics, and multimodal environments, we highlight the strengths, limitations, and best-fit scenarios for each technique. This survey aims to offer researchers a practical guide for selecting the most suitable graph-LLM approach depending on task requirements, data characteristics, and reasoning complexity.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 95 of its 137 references that are in the map. First posted on arXiv 17 Apr 2026.

Builds on

95 of 137 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025Combining LLM Semantic Reasoning with GNN Structural Modeling for Multi-View Multi-Label Feature Selection11 Nov
  2. 2025GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation26 Sep
  3. 2025Enrich-on-Graph: Query-Graph Alignment for Complex Reasoning with LLM Enriching25 Sep
  4. 2025AgREE: Agentic Reasoning for Knowledge Graph Completion on Emerging Entities6 Aug
  5. 2025Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphs12 Jun
  6. 2025Large Language Model-Enhanced Symbolic Reasoning for Knowledge Base Completion2 Jan
  7. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning30 May
  8. 2024InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment13 Feb
  9. 2023LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities22 May

Other references · 86

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  5. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  6. 2019Simplifying Graph Convolutional Networkscited by 1,470
  7. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  8. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  9. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
  10. 2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 480
  11. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 408
  12. 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
38 more
  1. 2023Tool Learning with Foundation Modelscited by 302
  2. 2023Faithful Chain-of-Thought Reasoningcited by 285
  3. 2023GraphGPT: Graph Instruction Tuning for Large Language Modelscited by 223
  4. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 217
  5. 2024LLaGA: Large Language and Graph Assistantcited by 177
  6. 2023LLMRec: Large Language Models with Graph Augmentation for Recommendationcited by 171
  7. 2022Learning on Large-scale Text-attributed Graphs via Variational Inferencecited by 153
  8. 2021A Comprehensive Survey of Scene Graphs: Generation and Applicationcited by 125
  9. 2024SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Codecited by 125
  10. 2024SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigationcited by 106
  11. 2024AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agentscited by 100
  12. 2023A Survey of Graph Meets Large Language Model: Progress and Future Directionscited by 84
  13. 2022Scene Graph Generation: A Comprehensive Surveycited by 73
  14. 2024A Survey of Large Language Models for Graphscited by 71
  15. 2024Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answeringcited by 59
  16. 2024GOFA: A Generative One-For-All Model for Joint Graph Language Modelingcited by 56
  17. 2026MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agentscited by 49
  18. 2023Text2KGBench: A Benchmark for Ontology-Driven Knowledge Graph Generation from Textcited by 48
  19. 2024HiGPT: Heterogeneous Graph Language Modelcited by 44
  20. 2023LLM-assisted Knowledge Graph Engineering: Experiments with ChatGPTcited by 42
  21. 2024From human experts to machines: An LLM supported approach to ontology and knowledge graph constructioncited by 40
  22. 2024SceneCraft: Layout-Guided 3D Scene Generationcited by 40
  23. 2024Knowledge Graph Large Language Model (KG-LLM) for Link Predictioncited by 36
  24. 2024GraphEdit: Large Language Models for Graph Structure Learningcited by 33
  25. 2023LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generationcited by 30
  26. 2024GraphEval: A Knowledge-Graph Based LLM Hallucination Evaluation Frameworkcited by 30
  27. 2023SGFormer: Semantic Graph Transformer for Point Cloud-based 3D Scene Graph Generationcited by 27
  28. 2025Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Taskscited by 27
  29. 2023Optimal Scene Graph Planning with Large Language Model Guidancecited by 26
  30. 20243DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understandingcited by 26
  31. 2023Iterative Zero-Shot LLM Prompting for Knowledge Graph Constructioncited by 25
  32. 2024Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks?cited by 22
  33. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applicationscited by 22
  34. 2024Distilling Large Language Models for Text-Attributed Graph Learningcited by 20
  35. 2024LLM and GNN are Complementary: Distilling LLM for Multimodal Graph Learningcited by 17
  36. 2025GraphCodeAgent: Dual Graph-Guided LLM Agent for Retrieval-Augmented Repo-Level Code Generationcited by 17
  37. 2024Scene Graph Generation with Role-Playing Large Language Modelscited by 16
  38. 2025From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memorycited by 16

50 most cited of 86 All 86 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

Similar, not cited

Close in wording, no citation either way

  1. 2026GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning
  2. 2026LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems
  3. 2026Are Large Language Models Suitable for Graph Computation? Progress and Prospects
  4. 2024GraphTeam: Facilitating Large Language Model-based Graph Analysis via Multi-Agent Collaboration
  5. 2025Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval
  6. 2023GraphLLM: Boosting Graph Reasoning Ability of Large Language Model
  7. 2023Talk like a Graph: Encoding Graphs for Large Language Models
  8. 2025GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic Tasks