Graph-Based Agent Memory

Follow this topic Ask about this topic

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

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

Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability
May 21, 2026Taewoon Kim, Vincent François-Lavet, Michael CochezPartially Observable RL Q-Learning
1HumemAI · 2Vrije Universiteit Amsterdam · 3ELLIS Institute Finland & Abo Akademi University
EXG: Self-Evolving Agents with Experience Graphs
May 18, 2026Yuxin Jin, Siyuan Zhang, Hanchen Wang +3Graph-Based Agent Memory Memory-Augmented Agents
University of Technology Sydney Sydney, Australia · The University of New South Wales Sydney, Australia
CogniFold: Always-On Proactive Memory via Cognitive Folding
May 13, 2026Suli Wang, Yiqun Duan, Yu Deng +5Cognitive Architectures for AI Agents Continual Learning
1OpenNorve · University of Cambridge · 3NVIDIA +1
Executable Agentic Memory for GUI Agent
May 12, 2026Zerui Qin, Sheng Yue, Xingyuan Hua +2GUI Agents LLM Agent Memory
1Tsinghua University, China · 2Sun Yat-sen University, China
SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory
May 12, 2026Juntong Wang, Haoyue Zhao, guanghui Pan +4Agent Memory Graph Retrieval-Augmented Generation
Institute for Artificial Intelligence, Peking University · School of Intelligence Science and Technology, Peking University · School of Computer Science and Technology, Beijing Institute of Technology
SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs
May 12, 2026Xiaoyuan Li, Moxin Li, Keqin Bao +4LLM Agent Skill Learning LLM Agent Skill Retrieval
University of Science and Technology of China · National University of Singapore · Alibaba Group
MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs
May 11, 2026Ruiyi Yang, Zechen Li, Hao Xue +2Agent Memory Continual Learning for LLM Agents
University of New South Wales · The Hong Kong University of Science and Technology (Guangzhou) · Mohamed Bin Zayed University of Artificial Intelligence
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
May 11, 2026Dongming Jiang, Yi Li, Guanpeng Li +2Agent Memory Graph-Based Agent Memory
Department of Computer Science, The University of Texas at Dallas · Department of Electrical and Computer Engineering, University of Florida · University of California, Davis
ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts
May 9, 2026Yang Luo, Zifeng Kang, Tiantian Ji +4Agent Memory Poisoning Graph-Based Agent Memory
Key Laboratory of Trustworthy Distributed Computing and Service (MoE), Beijing University of Posts and Telecommunications · Beijing University of Posts and Telecommunications · Zhongguancun Laboratory
MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs
May 8, 2026Junwei Liao, Haoting Shi, Ruiwen Zhou +9LLM Agent Memory Q-Learning
Shanghai Jiao Tong University · Shanghai Innovation Institute · National University of Singapore +3
MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents
May 2, 2026Hung Pham Van, Nguyen Manh Hieu, Khang Pham Tran Tuan +4Conversational Memory Graph Retrieval-Augmented Generation
1Independent Researcher · 2Hanoi University of Science and Technology · 3VNU University of Engineering and Technology +1
GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs
Apr 26, 2026Tao Feng, Haozhen Zhang, Zijie Lei +2Multi-Agent LLM Systems LLM Agent Orchestration
Department of Computer Science University of Illinois Urbana-Champaign Urbana, IL, USA
ContextWeaver: Selective and Dependency-Structured Memory Construction for LLM Agents
Apr 24, 2026Yating Wu, Yuhao Zhang, Sayan Ghosh +4LLM Agent Memory Graph-Based Agent Memory
UT Austin · AWS AI Labs
EngramaBench: Evaluating Long-Term Conversational Memory with Structured Graph Retrieval
Apr 23, 2026Julian AcunaLLM Evaluation Memorization in Language Models
WorldDB: A Vector Graph-of-Worlds Memory Engine with Ontology-Aware Write-Time Reconciliation
Apr 20, 2026Harish Santhanalakshmi GanesanTemporal KGs Persistent Memory for Language Models
Independent Researcher
EmbodiedLGR: Integrating Lightweight Graph Representation and Retrieval for Semantic-Spatial Memory in Robotic Agents
Apr 20, 2026Paolo Riva, Leonardo Gargani, Matteo Frosi +1Graph Retrieval-Augmented Generation Embodied QA
Department of Electronics, Information, and Bioengineering (DEIB), Politecnico di Milano, Milan, Italy
HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents
Apr 18, 2026Jinchang Zhu, Jindong Li, Cheng Zhang +2Memorization in Language Models Hebbian Learning
The Hong Kong University of Science and Technology (Guangzhou) · Jilin University · The Chinese University of Hong Kong
APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AI
Apr 15, 2026Pratyay Banerjee, Masud Moshtaghi, Shivashankar Subramanian +2Long-Term Conversational Memory Graph-Based Agent Memory
Amazon, AGI, Sunnyvale, USA
GAM: Hierarchical Graph-based Agentic Memory for LLM Agents
Apr 14, 2026Zhaofen Wu, Hanrong Zhang, Fulin Lin +9Agent Memory Management Graph-Based Agent Memory
Zhejiang University · University of Illinois Chicago · Rutgers University +2
Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory
Apr 13, 2026Weixian Waylon Li, Jiaxin Zhang, Xianan Jim Yang +2Temporal KGs Graph-Based Agent Memory
University of Edinburgh · LIGHTSPEED · Independent Researcher
StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding
Apr 10, 2026Junxi Wang, Te Sun, Jiayi Zhu +6Agent Memory Management Memory-Augmented Video Understanding
Shanghai Jiao Tong University · Fudan University · Shanghai AI Laboratory +2
HyperMem: Hypergraph Memory for Long-Term Conversations
Apr 9, 2026Juwei Yue, Chuanrui Hu, Jiawei Sheng +5Long-Term Conversational Memory Graph-Based Agent Memory
Institute of Information Engineering, Chinese Academy of Sciences · School of Cyber Security, University of Chinese Academy of Sciences · EverMind AI
Task-Adaptive Retrieval over Agentic Multi-Modal Web Histories via Learned Graph Memory
Apr 9, 2026Saman Forouzandeh, Kamal Berahmand, Mahdi JaliliAdaptive Retrieval Multimodal IR
School of Engineering, Royal Melbourne Institute of Technology University, Melbourne, Australia
SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents
Apr 9, 2026Xinshun Feng, Xinhao Song, Lijun Li +2Self-Evolving Agents Memory-Augmented Agents
Shanghai Artificial Intelligence Laboratory · Shanghai Jiaotong University
Prism: An Evolutionary Memory Substrate for Multi-Agent Open-Ended Discovery
Apr 8, 2026Suyash MishraAgent Memory Management Graph-Based Agent Memory
AI Researcher · Basel, Switzerland
Hypothesis Graph Refinement: Hypothesis-Driven Exploration with Cascade Error Correction for Embodied Navigation
Apr 5, 2026Peixin Chen, Guoxi Zhang, Jianwei Ma +1Embodied Navigation Graph-Based Agent Memory
Harbin Institute of Technology · Beijing Institute for General Artificial Intelligence · Peking University
ByteRover: Agent-Native Memory Through LLM-Curated Hierarchical Context
Apr 2, 2026Andy Nguyen, Danh Doan, Hoang Pham +8LLM Agent Memory Agent Memory Management
ByteRover
APEX-EM: Non-Parametric Online Learning for Autonomous Agents via Structured Procedural-Episodic Experience Replay
Mar 31, 2026Pratyay Banerjee, Masud Moshtaghi, Ankit ChadhaReplay-Based Continual Learning Persistent Memory for Language Models
Amazon, AGI / Sunnyvale, USA
GAAMA: Graph Augmented Associative Memory for Agents
Mar 29, 2026Swarna Kamal Paul, Shubhendu Sharma, Nitin SareenGraph-Based Agent Memory Long-Term Conversational Memory
Nagarro
Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP
Mar 28, 2026Martin Vogel, Falk Meyer-Eschenbach, Severin Kohler +2AI Coding Agents Graph-Based Agent Memory
Independent Researcher, Berlin, Germany · Institute of Medical Informatics, Charité – Universitätsmedizin Berlin, Berlin, Germany · Clinical Study Center, Berlin Institute of Health, Berlin, Germany +3

May 21, 2026J/K move · Enter open · S save

Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability

Taewoon Kim, Vincent François-Lavet, Michael Cochez

1HumemAI · 2Vrije Universiteit Amsterdam · 3ELLIS Institute Finland & Abo Akademi University

Partially Observable RL Q-Learning Graph-Based Agent Memory Memory-Augmented Agents Temporal KGs Memory Consolidation

Open paper AskPDF arXiv

Reinforcement learning under partial observability requires deciding what information to retain, yet most memory-based approaches do not explicitly model short-term-to-long-term transfer of symbolic observations. We study this transfer process in a temporal knowledge-graph memory setting and cast it as a neuro-symbolic value-based decision problem: for each observed triple, the agent chooses whether to keep or drop it before long-term insertion. To handle variable-sized short-term buffers, we use a per-item Q-learning design with shared parameters and a practical temporal-difference update over matched items across consecutive steps. On the RoomKG benchmark at long-term memory capacity 128, learned transfer decisions outperform symbolic and neural baselines, including symbolic baselines with temporal annotations and history-based LSTM/Transformer baselines. Across transfer-policy ablations, a lightweight local short-term-only variant performs best, and step-level behavior shows that the policy keeps navigation- and query-relevant facts while discarding lower-value candidate facts, supporting explicit and interpretable memory decisions under memory constraints.