mlsanityData to 7 Oct 2026

Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities

arXiv 2506.18019 ↗First posted 22 Jun 2025cs.AIcited by 23

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

AI agents have experienced a paradigm shift, from early dominance by reinforcement learning (RL) to the rise of agents powered by large language models (LLMs), and now further advancing towards a synergistic fusion of RL and LLM capabilities. This progression has endowed AI agents with increasingly strong abilities. Despite these advances, to accomplish complex real-world tasks, agents are required to plan and execute effectively, maintain reliable memory, and coordinate smoothly with other agents. Achieving these capabilities involves contending with ever-present intricate information, operations, and interactions. In light of this challenge, data structurization can play a promising role by transforming intricate and disorganized data into well-structured forms that agents can more effectively understand and process. In this context, graphs, with their natural advantage in organizing, managing, and harnessing intricate data relationships, present a powerful data paradigm for structurization to support the capabilities demanded by advanced AI agents. To this end, this survey presents a first systematic review of how graphs can empower AI agents. Specifically, we explore the integration of graph techniques with core agent functionalities, highlight notable applications, and identify prospective avenues for future research. By comprehensively surveying this burgeoning intersection, we hope to inspire the development of next-generation AI agents equipped to tackle increasingly sophisticated challenges with graphs. Related resources are collected and continuously updated for the community in the Github link.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 188 of its 242 references that are in the map. First posted on arXiv 22 Jun 2025.

Builds on

188 of 242 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environments1 Apr
  2. 2025IGDA: Interactive Graph Discovery through Large Language Model Agents24 Feb
  3. 2025Schema-Guided Scene-Graph Reasoning based on Multi-Agent Large Language Model System5 Feb
  4. 2024GraphAgent: Agentic Graph Language Assistant22 Dec
  5. 2024GraphTeam: Facilitating Large Language Model-based Graph Analysis via Multi-Agent Collaboration23 Oct
  6. 2024Scalable and Accurate Graph Reasoning with LLM-based Multi-Agents7 Oct
  7. 2024KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph17 Feb
  8. 2023Graph Agent: Explicit Reasoning Agent for Graphs25 Oct
  9. 2023A Versatile Graph Learning Approach through LLM-based Agent8 Sep

Other references · 179

  1. 2017Attention Is All You Needcited by 59,932
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Graph Attention Networkscited by 8,854
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  6. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  7. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  8. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  9. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  10. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  11. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  12. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
38 more
  1. 2016Variational Graph Auto-Encoderscited by 1,373
  2. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  3. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,280
  4. 2023A Survey on Evaluation of Large Language Modelscited by 1,227
  5. 2023AgentBench: Evaluating LLMs as Agentscited by 1,211
  6. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
  7. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  8. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
  9. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
  10. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  11. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
  12. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 574
  13. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 551
  14. 2017A Brief Survey of Deep Reinforcement Learningcited by 466
  15. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
  16. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 443
  17. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 424
  18. 2024Understanding the planning of LLM agents: A surveycited by 414
  19. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  20. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 385
  21. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  22. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  23. 2022PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Changecited by 372
  24. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memorycited by 372
  25. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 326
  26. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learningcited by 322
  27. 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
  28. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 310
  29. 2023SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planningcited by 289
  30. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaborationcited by 281
  31. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
  32. 2024ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilitiescited by 272
  33. 2025Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directionscited by 257
  34. 2017Automatic Goal Generation for Reinforcement Learning Agentscited by 252
  35. 2023One for All: Towards Training One Graph Model for All Classification Taskscited by 239
  36. 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 235
  37. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agentscited by 228
  38. 2023PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimizationcited by 226

50 most cited of 179 All 179 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 18.

23 papers.

Sort:

By area:

  1. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 40
  2. 2026Code as Agent Harnesscited by 40
  3. 2025Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoningcited by 22
  4. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applicationscited by 22
  5. 2025RAG-Anything: All-in-One RAG Frameworkcited by 18
  6. 2026AgentGuardian: Learning Access Control Policies to Govern AI Agent Behaviorcited by 9
  7. 2026CARD: Towards Conditional Design of Multi-agent Topological Structurescited by 7
  8. 2025UFO3: Weaving the Digital Agent Galaxycited by 6
  9. 2026Mixture of Sequence: Theme-Aware Mixture-of-Experts for Long-Sequence Recommendationcited by 4
  10. 2026Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspectivecited by 4
  11. 2025Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagationcited by 3
  12. 2026Think Locally, Explain Globally: Graph-Guided LLM Investigations via Local Reasoning and Belief Propagationcited by 3
11 more
  1. 2026MOC: Multi-Order Communication in LLM-based Multi-Agent Systemscited by 3
  2. 2026RubricsTree: Scalable and Evolving Open-Ended Evaluation of Personal Health Agents across Health Memory and Medical Skillscited by 3
  3. 2025PRAXIS: Integrating Program Analysis with Observability for Root-Cause Analysiscited by 2
  4. 2026The Semantic Lifecycle in Embodied AI: Acquisition, Representation and Storage via Foundation Modelscited by 2
  5. 2026Beyond Individual Mimicry: Constructing Human-Like Social network with Graph-Augmented LLM Agentscited by 1
  6. 2026Toward User Preference Alignment in LLM Recommendation via Explicit Context Feedbackcited by 1
  7. 2026Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligencecited by 1
  8. 2026Multi-Agent Agentic Graph Learning via Structural Signaturescited by 1
  9. 2026Towards a Declarative Agentic Layer for Intelligent Agents in MCP-Based Server Ecosystemscited by 0
  10. 2026LLMs+Graphs: Toward Graph-Native, Synergistic AI Systemscited by 0
  11. 2026Towards Self-Evolving Agents: A Human-Inspired Adaptive Exploration-Exploitation Framework for Genetic Network Programmingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects
  2. 2026AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning
  3. 2025A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and Beyond
  4. 2025GAP: Graph-Based Agent Planning with Parallel Tool Use and Reinforcement Learning
  5. 2026Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval
  6. 2026GraphMAS: A Systematic Benchmark of Multi-Agent Coordination for Graph Learning
  7. 2026Graph World Models: Concepts, Taxonomy, and Future Directions
  8. 2026SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topology