mlsanityData to 14 Oct 2026

Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects

arXiv 2507.21407 ↗First posted 29 Jul 2025cs.AIcited by 14

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Autonomous agents based on large language models (LLMs) have demonstrated impressive capabilities in a wide range of applications, including web navigation, software development, and embodied control. While most LLMs are limited in several key agentic procedures, such as reliable planning, long-term memory, tool management, and multi-agent coordination, graphs can serve as a powerful auxiliary structure to enhance structure, continuity, and coordination in complex agent workflows. Given the rapid growth and fragmentation of research on Graph-augmented LLM Agents (GLA), this paper offers a timely and comprehensive overview of recent advances and also highlights key directions for future work. Specifically, we categorize existing GLA methods by their primary functions in LLM agent systems, including planning, memory, and tool usage, and then analyze how graphs and graph learning algorithms contribute to each. For multi-agent systems, we further discuss how GLA solutions facilitate the orchestration, efficiency optimization, and trustworthiness of MAS. Finally, we highlight key future directions to advance this field, from improving structural adaptability to enabling unified, scalable, and multimodal GLA systems. We hope this paper can serve as a roadmap for future research on GLA and foster a deeper understanding of the role of graphs in LLM agent systems.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 74 of its 90 references that are in the map. First posted on arXiv 29 Jul 2025.

Builds on

74 of 90 references.

Closest ancestors · 17

Same direction, newest first

  1. 2025Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation24 Jul
  2. 2025AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction21 Jun
  3. 2025RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensation30 May
  4. 2025ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks4 Mar
  5. 2025Plan-over-Graph: Towards Parallelable LLM Agent Schedule20 Feb
  6. 2025Multi-agent Architecture Search via Agentic Supernet6 Feb
  7. 2025Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies4 Feb
  8. 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks15 Oct
  9. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems3 Oct
  10. 2024Improving Multi-Agent Debate with Sparse Communication Topology17 Jun
  11. 2024Scaling Large Language Model-based Multi-Agent Collaboration11 Jun
  12. 2024Can Graph Learning Improve Planning in LLM-based Agents?29 May
5 more
  1. 2024Understanding the planning of LLM agents: A survey5 Feb
  2. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges21 Jan
  3. 2023The Rise and Potential of Large Language Model Based Agents: A Survey14 Sep
  4. 2023A Survey on Large Language Model based Autonomous Agents22 Aug
  5. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate14 Aug

Other references · 57

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  4. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  6. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  7. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  8. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  9. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  10. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  11. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  12. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 680
38 more
  1. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  2. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 545
  3. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 452
  4. 2024AFlow: Automating Agentic Workflow Generationcited by 432
  5. 2023AppAgent: Multimodal Agents as Smartphone Userscited by 415
  6. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  7. 2024Agent-SafetyBench: Evaluating the Safety of LLM Agentscited by 306
  8. 2024Debating with More Persuasive LLMs Leads to More Truthful Answerscited by 266
  9. 2020A Note on Over-Smoothing for Graph Neural Networkscited by 249
  10. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 222
  11. 2023SafetyBench: Evaluating the Safety of Large Language Modelscited by 199
  12. 2020Learning to Drop: Robust Graph Neural Network via Topological Denoisingcited by 127
  13. 2021DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networkscited by 118
  14. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 116
  15. 2022A Survey of Multi-Agent Deep Reinforcement Learning with Communicationcited by 104
  16. 2024KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graphcited by 93
  17. 2025AgentAuditor: Human-Level Safety and Security Evaluation for LLM Agentscited by 90
  18. 2025LocAgent: Graph-Guided LLM Agents for Code Localizationcited by 86
  19. 2024Self-Evolving Multi-Agent Collaboration Networks for Software Developmentcited by 74
  20. 2021A Survey on Graph Structure Learning: Progress and Opportunitiescited by 71
  21. 2025FlowReasoner: Reinforcing Query-Level Meta-Agentscited by 63
  22. 2024ToolNet: Connecting Large Language Models with Massive Tools via Tool Graphcited by 60
  23. 2023ControlLLM: Augment Language Models with Tools by Searching on Graphscited by 59
  24. 2025G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systemscited by 59
  25. 2025EvoFlow: Evolving Diverse Agentic Workflows On The Flycited by 55
  26. 2023GSLB: The Graph Structure Learning Benchmarkcited by 50
  27. 2025Manipulating Multimodal Agents via Cross-Modal Prompt Injectioncited by 44
  28. 2025SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integrationcited by 43
  29. 2024RATT: A Thought Structure for Coherent and Correct LLM Reasoningcited by 41
  30. 2025AgentSafe: Safeguarding Large Language Model-based Multi-agent Systems via Hierarchical Data Managementcited by 38
  31. 2025AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructionscited by 38
  32. 2024ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesiscited by 30
  33. 2024NetSafe: Exploring the Topological Safety of Multi-agent Networkscited by 29
  34. 2025Debate Only When Necessary: Adaptive Multiagent Collaboration for Efficient LLM Reasoningcited by 27
  35. 2025A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?cited by 23
  36. 2025VFlow: Discovering Optimal Agentic Workflows for Verilog Generationcited by 19
  37. 2024Graph Sparsification via Mixture of Graphscited by 17
  38. 2025GNNs as Predictors of Agentic Workflow Performancescited by 17

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 9.

14 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 303
  2. 2025A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Modelscited by 14
  3. 2026CARD: Towards Conditional Design of Multi-agent Topological Structurescited by 9
  4. 2025Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memorycited by 6
  5. 2025Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagationcited by 4
  6. 2026From Agent Loops to Structured Graphs:A Scheduler-Theoretic Framework for LLM Agent Executioncited by 4
  7. 2026Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspectivecited by 4
  8. 2026CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systemscited by 3
  9. 2026Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligencecited by 3
  10. 2025Test-time GNN Model Evaluation on Dynamic Graphscited by 1
  11. 2026Towards Self-Evolving Agents: A Human-Inspired Adaptive Exploration-Exploitation Framework for Genetic Network Programmingcited by 0
  12. 2026Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigationcited by 0
2 more
  1. 2026Building Trustworthy Graph-Agentic RAG for Social Good: Architectures, Failure Propagation, and Assurance by Constructioncited by 0
  2. 2026Graph-Based Personalized Memory for LLM Agents: Representation, Evolution, Retrieval, and Evaluationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challenges
  2. 2025Generalizability of Large Language Model-Based Agents: A Comprehensive Survey
  3. 2023BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents
  4. 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects
  5. 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users
  6. 2024Language Agents as Optimizable Graphs
  7. 2026AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning
  8. 2025AMAS: Adaptively Determining Communication Topology for LLM-based Multi-Agent System