Graph-Based Agent Memory

Ask about this topic

Overview

Graph-based agent memory studies how AI agents can store and reuse information across long conversations, tool-use episodes, tasks, and changing environments. Systems commonly represent events, facts, skills, and their temporal or causal relationships in typed graphs or hypergraphs, then retrieve relevant subgraphs through traversal, ranking, or learned query-conditioned routing. Some also update, consolidate, revise, or forget memories using feedback, reinforcement learning, provenance, and validity checks; evaluations span conversational benchmarks such as LoCoMo and LongMemEval as well as tool-use and embodied-navigation tasks. Structured links can help with multi-hop reasoning and experience reuse, but graph construction and maintenance add costs, and results still depend on extraction quality, retrieval design, and fair comparisons with simpler vector or full-context methods.

Latest papers

CardsList

134 papers27 papers in the last four weeks, up 23% on the four weeks before. 0.2% of all new papers.

  1. Environment Maps: Structured Environmental Representations for Long-Horizon Agents

    Mar 24, 2026Yenchia Feng, Chirag Sharma, Karime MaamariLong-Horizon LLM AgentsLLM Agent Planning

    Distyl AI

  2. GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoning

    Mar 23, 2026Xiao Han, Yuzheng Fan, Sendong Zhao +2Memory-Augmented Language Model AgentsGraph-Based Agent Memory

    Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, China

  3. All-Mem: Agentic Lifelong Memory via Dynamic Topology Evolution

    Mar 20, 2026Can Lv, Heng Chang, Shengyu Tao +5Agent Memory ManagementLong-Term Conversational Memory

    Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing · Beihang University · Tsinghua University +1

  4. Graph-Native Cognitive Memory for AI Agents: Formal Belief Revision Semantics for Versioned Memory Architectures

    Mar 18, 2026Young Bin ParkGraph-Based Agent MemoryAgent Memory Management

  5. AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents

    Mar 17, 2026Shannan Yan, Jingchen Ni, Leqi Zheng +6LLM Agent MemoryLong-Term Conversational Memory

    Tsinghua University · WeChat Vision, Tencent Inc.

  6. D-MEM: Dopamine-Gated Agentic Memory via Reward Prediction Error Routing

    Mar 15, 2026Yuru Song, Qi XinAgent Memory ManagementMemory-Augmented Language Model Agents

    UC San Diego · Carnegie Mellon University

  7. BrainMem: Brain-Inspired Evolving Memory for Embodied Agent Task Planning

    Mar 12, 2026Xiaoyu Ma, Lianyu Hu, Wenbing Tang +4Long-Term Memory for Embodied AgentsMemory-Augmented Language Model Agents

    Nanyang Technological University, Singapore · Tianjin University, Tianjin, China

  8. Hybrid Self-evolving Structured Memory for GUI Agents

    Mar 11, 2026Sibo Zhu, Wenyi Wu, Kun Zhou +2GUI AgentsAgent Memory Management

    University of California, San Diego

  9. A Hierarchical Error-Corrective Graph Framework for Autonomous Agents with LLM-Based Action Generation

    Mar 9, 2026Cong Cao, Jingyao Zhang, Kun TongFailure Attribution for LLM AgentsLLM Agent Reliability

    Independent Researcher, Hangzhou, Zhejiang, China · Beihang University, Hangzhou, Zhejiang, China

  10. CraniMem: Cranial Inspired Gated and Bounded Memory for Agentic Systems

    Mar 3, 2026Pearl Mody, Mihir Panchal, Rishit Kar +2Agent MemoryAgent Memory Management

    Dwarkadas Jivanlal Sanghvi College of Engineering

  11. SSMG-Nav: Enhancing Lifelong Object Navigation with Semantic Skeleton Memory Graph

    Mar 2, 2026Haochen Niu, Lantao Zhang, Xingwu Ji +3Robot NavigationObject-Goal Navigation

    Brain-Inspired Application Technology Center (BATC), Shanghai Jiao Tong University, Shanghai 200240, China

  12. AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications

    Feb 26, 2026Yujie Zhao, Boqin Yuan, Junbo Huang +9Agent MemoryLong-Horizon Agent Evaluation

    UCSD · Recursive.

  13. Contextual Memory Virtualisation: DAG-Based State Management and Structurally Lossless Trimming for LLM Agents

    Feb 25, 2026Cosmo SantoniLLM Context ManagementAgent Memory Management

    Imperial College London

  14. Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory

    Dec 8, 2025Sijia Li, Yuchen Huang, Zifan Liu +6RL ExplorationGraph-Based Agent Memory

    Hong Kong University of Science and Technology · Microsoft Research Asia · Work done during internship at Microsoft.