mlsanityData to 7 Oct 2026

G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems

arXiv 2506.07398 ↗First posted 9 Jun 2025cs.MA cs.CL cs.LGcited by 112

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

Large language model (LLM)-powered multi-agent systems (MAS) have demonstrated cognitive and execution capabilities that far exceed those of single LLM agents, yet their capacity for self-evolution remains hampered by underdeveloped memory architectures. Upon close inspection, we are alarmed to discover that prevailing MAS memory mechanisms (1) are overly simplistic, completely disregarding the nuanced inter-agent collaboration trajectories, and (2) lack cross-trial and agent-specific customization, in stark contrast to the expressive memory developed for single agents. To bridge this gap, we introduce G-Memory, a hierarchical, agentic memory system for MAS inspired by organizational memory theory, which manages the lengthy MAS interaction via a three-tier graph hierarchy: insight, query, and interaction graphs. Upon receiving a new user query, G-Memory performs bi-directional memory traversal to retrieve both textithigh-level, generalizable insights that enable the system to leverage cross-trial knowledge, and textitfine-grained, condensed interaction trajectories that compactly encode prior collaboration experiences. Upon task execution, the entire hierarchy evolves by assimilating new collaborative trajectories, nurturing the progressive evolution of agent teams. Extensive experiments across five benchmarks, three LLM backbones, and three popular MAS frameworks demonstrate that G-Memory improves success rates in embodied action and accuracy in knowledge QA by up to 20.89% and 10.12%, respectively, without any modifications to the original frameworks. Our codes are available at https://github.com/bingreeky/GMemory.

Key facts. Cited by 112 papers in the map (data through 7 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 61 of its 80 references that are in the map. First posted on arXiv 9 Jun 2025.

Builds on

61 of 80 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory28 Apr
  2. 2025MemInsight: Autonomous Memory Augmentation for LLM Agents27 Mar
  3. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  4. 2024Self-evolving Agents with reflective and memory-augmented abilities1 Sep
  5. 2024A Survey on the Memory Mechanism of Large Language Model based Agents21 Apr

Other references · 56

  1. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  2. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  3. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  4. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  5. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  6. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  7. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
  8. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  9. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  10. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  11. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  12. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
38 more
  1. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
  2. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
  3. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  4. 2024Mixture-of-Agents Enhances Large Language Model Capabilitiescited by 420
  5. 2024Understanding the planning of LLM agents: A surveycited by 414
  6. 2024Automated Design of Agentic Systemscited by 360
  7. 2024AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agentscited by 319
  8. 2022ScienceWorld: Is your Agent Smarter than a 5th Grader?cited by 298
  9. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 288
  10. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 253
  11. 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 235
  12. 2023Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Drivingcited by 231
  13. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agentscited by 228
  14. 2024Data Interpreter: An LLM Agent For Data Sciencecited by 222
  15. 2024Agent Q: Advanced Reasoning and Learning for Autonomous AI Agentscited by 201
  16. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Taskscited by 190
  17. 2023Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Controlcited by 180
  18. 2024The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Surveycited by 164
  19. 2025Multi-agent Architecture Search via Agentic Supernetcited by 164
  20. 2023Progressive-Hint Prompting Improves Reasoning in Large Language Modelscited by 147
  21. 2024Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Makingcited by 142
  22. 2023ChatDB: Augmenting LLMs with Databases as Their Symbolic Memorycited by 136
  23. 2023RecMind: Large Language Model Powered Agent For Recommendationcited by 129
  24. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systemscited by 129
  25. 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networkscited by 110
  26. 2024EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithmscited by 109
  27. 2024Symbolic Learning Enables Self-Evolving Agentscited by 104
  28. 2023MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversationcited by 94
  29. 2024Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agentscited by 91
  30. 2025MasRouter: Learning to Route LLMs for Multi-Agent Systemscited by 80
  31. 2023Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communicationcited by 78
  32. 2024Self-Evolving Multi-Agent Collaboration Networks for Software Developmentcited by 73
  33. 2023Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorldcited by 65
  34. 2024KnowAgent: Knowledge-Augmented Planning for LLM-Based Agentscited by 61
  35. 2025EvoFlow: Evolving Diverse Agentic Workflows On The Flycited by 49
  36. 2023Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worldscited by 45
  37. 2025ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoningcited by 41
  38. 2025SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoningcited by 41

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 22; 2026: 90.

112 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 285
  2. 2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learningcited by 252
  3. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 195
  4. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 163
  5. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 155
  6. 2025EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecyclecited by 129
  7. 2025MemGen: Weaving Generative Latent Memory for Self-Evolving Agentscited by 99
  8. 2025Recursive Language Modelscited by 94
  9. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 54
  10. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  11. 2026Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agentscited by 44
  12. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 40
38 more
  1. 2026Dynamic Dual-Granularity Skill Bank for Agentic RLcited by 33
  2. 2025VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Modelscited by 31
  3. 2025CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewardscited by 27
  4. 2025MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learningcited by 26
  5. 2026Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineeringcited by 26
  6. 2026AgentOCR: Reimagining Agent History via Optical Self-Compressioncited by 22
  7. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applicationscited by 22
  8. 2025Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memorycited by 19
  9. 2026A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applicationscited by 17
  10. 2025SEDM: Scalable Self-Evolving Distributed Memory for Agentscited by 16
  11. 2025From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memorycited by 16
  12. 2026HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agentscited by 16
  13. 2026Learning to Continually Learn via Meta-learning Agentic Memory Designscited by 16
  14. 2025TeleMem: Building Long-Term and Multimodal Memory for Agentic AIcited by 14
  15. 2025AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agentscited by 12
  16. 2026LatentMem: Customizing Latent Memory for Multi-Agent Systemscited by 12
  17. 2026EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agentscited by 12
  18. 2025Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberationcited by 11
  19. 2026E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent Memorycited by 10
  20. 2026Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agentscited by 9
  21. 2026MemSyco-Bench: Benchmarking Sycophancy in Agent Memorycited by 9
  22. 2025LatentEvolve: Self-Evolving Test-Time Scaling in Latent Spacecited by 8
  23. 2025Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AIcited by 8
  24. 2026Governed Shared Memory for Multi-Agent LLM Systemscited by 8
  25. 2026MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic Reasoningcited by 7
  26. 2026ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agentscited by 6
  27. 2026Retrieval-Augmented LLM Agents: Learning to Learn from Experiencecited by 6
  28. 2026Memory Intelligence Agentcited by 6
  29. 2026Self-Evolving Multi-Agent Systems via Decentralized Memorycited by 6
  30. 2025Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agentcited by 5
  31. 2026Large Language Model Agents Are Not Always Faithful Self-Evolverscited by 5
  32. 2026A-MapReduce: Executing Wide Search via Agentic MapReducecited by 5
  33. 2026Pancake: Hierarchical Memory System for Multi-Agent LLM Servingcited by 5
  34. 2026GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoningcited by 5
  35. 2026Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systemscited by 5
  36. 2026Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system securitycited by 5
  37. 2026Co-Evolving Skill Generation and Policy Optimizationcited by 5
  38. 2026Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agentscited by 5

50 most cited of 112 All 112 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026MemCo: Memory-Centric Collaboration for Generalizing LLM Agents to Unseen Environments
  2. 2026AMA: Adaptive Memory via Multi-Agent Collaboration
  3. 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
  4. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
  5. 2026Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline
  6. 2026AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications
  7. 2026MemGym: a Long-Horizon Memory Environment for LLM Agents
  8. 2026Multi-Agent Memory from a Computer Architecture Perspective: Visions and Challenges Ahead