Skip to content
Projects

OpenDataBox/awesome-agent-memory

View on GitHub

OpenDataBox/awesome-agent-memory has 62 GitHub stars and 18 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-16 03:22 UTC. Last push 2026-11-15.

How these counts are measured

Measured star growth

in 24h
0
in 7 days
Update delayed
in 15 days
Update delayed
in 1 month
Update delayed

Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.

About

Awesome Paper List of Agent Memory Systems along Four Axes

AI

README.md

Original

Awesome Agent Memory Awesome

A curated taxonomy of agent memory systems, organized along four axes: (1) memory system architectures — from flat sequential context, to structural topological graphs/trees, to multi-paradigm hybrid containers; (2) reference baselines for comparison; (3) benchmarks for evaluation; and (4) surveys on agent memory Stars Forks Contributors Last Commit arXiv.

📣 Get Involved

  • 📊 Looking for a testbed to evaluate agent memory systems? See our companion repo OpenDataBox/MemoryData — an integrated platform of memory systems and datasets.
  • 📌 Missing a paper, method, or benchmark? Open an issue to request it.
  • 🤝 Want to contribute directly? Submit a Pull Request — community PRs are warmly welcomed!

Table of Contents

1. Memory Systems and Methods

1.1 Sequential Memory Systems

1.1.1 Discrete Textual Memory

Memory represented as a flat sequence, textual summary, note, trajectory, or experience record without an explicit graph or tree topology.

  1. Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval
    Yingyi Zhang, Junyi Li, Wenlin Zhang, et al. ICLR 2026. [Paper]

  2. Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
    Zeyuan Liu, Jeonghye Kim, Xufang Luo, et al. ICLR 2026. [Paper]

  3. Distilling Feedback into Memory-as-a-Tool
    Víctor Gallego. ICLR 2026. [Paper]

  4. The Pensieve Paradigm: Stateful Language Models Mastering Their Own Context
    Xiaoyuan Liu, Tian Liang, Dongyang Ma, et al. ICLR 2026. [Paper]

  5. Real-Time Procedural Learning From Experience for AI Agents
    Dasheng Bi, Yubin Hu, Mohammed N. Nasir. ICLR 2026. [Paper]

  6. ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
    Siru Ouyang, Jun Yan, I-Hung Hsu, et al. ICLR 2026. [Paper]

  7. MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent
    Hongli Yu, Tinghong Chen, Jiangtao Feng, et al. ICLR 2026. [Paper] [Code]

  8. Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
    Qirui Mi, Zhijian Ma, Mengyue Yang, et al. ICML 2026. [Paper]

  9. EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle
    Rong Wu, Xiaoman Wang, Jianbiao Mei, et al. ICML 2026. [Paper]

  10. History-Aware Reasoning for GUI Agents
    Ziwei Wang, Leyang Yang, Xiaoxuan Tang, et al. AAAI 2026. [Paper]

  11. ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning
    Juyuan Wang, Rongchen Zhao, Wei Wei, et al. AAAI 2026. [Paper]

  12. MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning
    Qianhao Yuan, Jie Lou, Zichao Li, et al. ACL 2026. [Paper]

  13. Who Remembers What? Multi-Granularity Memory Extraction for Multi-User, Multi-Agent Interaction
    Yunzhe Wang, Mesut Erhan Unal, Sheng Zhang, et al. arXiv 2026. [Paper]

  14. AutoMem: Automated Learning of Memory as a Cognitive Skill
    Shengguang Wu, Hao Zhu, Yuhui Zhang, et al. arXiv 2026. [Paper]

  15. MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management
    Guangyi Liu, Gao Wu, Congxiao Liu, et al. arXiv 2026. [Paper]

  16. CoreMem: Riemannian Retrieval and Fisher-Guided Distillation for Long-Term Memory in Dialogue Agents
    Jiaqi Chen, Yongqin Zeng, Shaoshen Chen, et al. arXiv 2026. [Paper]

  17. TokenPilot: Cache-Efficient Context Management for LLM Agents
    Buqiang Xu, Zirui Xue, Dianmou Chen, et al. arXiv 2026. [Paper]

  18. HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents
    Jiangze Yan, Yi Shen, Wenjing Zhang, et al. arXiv 2026. [Paper]

  19. T-Mem: Memory That Anticipates, Not Archives
    Weidong Guo, Dakai Wang, Zixuan Wang, et al. arXiv 2026. [Paper]

  20. MemRefine: LLM-Guided Compression for Long-Term Agent Memory
    Minjae Kim, Jinheon Baek, Soyeong Jeong, et al. arXiv 2026. [Paper]

  21. Multi-Turn Reasoning When Context Arrives in Pieces: Scalable Sharding and Memory-Augmented RL
    Shu Tong Luo, Wenqin Liu, Rui Liu, et al. arXiv 2026. [Paper]

  22. PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents
    Ripon Chandra Malo, Tong Qiu. arXiv 2026. [Paper]

  23. Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory
    Suozhao Ji, Baodong Wu, Zehao Wang, et al. arXiv 2026. [Paper]

  24. Rosetta Memory: Adaptive Memory for Cross-LLM Agents
    Hao Yang, Shiqi Shen, Haoxuan Li, et al. arXiv 2026. [Paper]

  25. TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memory
    Ziming Wang. arXiv 2026. [Paper]

  26. EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents
    Yilong Li, Suman Banerjee, Tong Che. arXiv 2026. [Paper]

  27. RAMPART: Registry-based Agentic Memory with Priority-Aware Runtime Transformation
    Nikodem Tomczak. arXiv 2026. [Paper]

  28. Training-Free Lexical-Dense Fusion for Conversational-Memory Retrieval
    Christian Lysenstøen. arXiv 2026. [Paper]

  29. DMF: A Deterministic Memory Framework for Conversational AI Agents
    Matteo Stabile, Enrico Zimuel. arXiv 2026. [Paper]

  30. InfoMem: Training Long-Context Memory Agents with Answer-Conditioned Information Gain
    Tiancheng Han, Yong Li, Wuzhou Yu, et al. arXiv 2026. [Paper]

  31. MemTrain: Self-Supervised Context Memory Training
    Ziheng Li, Xingrun Xing, Haoqing Wang, et al. arXiv 2026. [Paper]

  32. Memory Retrieval for Changing Preferences
    Yuehan Qin, Li Li, Linxin Song, et al. arXiv 2026. [Paper]

  33. Joint Agent Memory and Exploration Learning via Novelty Signals
    Shizuo Tian, Xiaohong Weng, Rui Kong, et al. arXiv 2026. [Paper]

  34. MemPro: Agentic Memory Systems as Evolvable Programs
    Qingshan Liu, Guoqing Wang, Wen Wu, et al. arXiv 2026. [Paper]

  35. CASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment
    Siyuan Guo, Yali Du, Hechang Chen, et al. arXiv 2026. [Paper]

  36. MemReranker: Reasoning-Aware Reranking for Agent Memory Retrieval
    Chunyu Li, Mengyuan Zhang, Jingyi Kang, et al. arXiv 2026. [Paper]

  37. Belief Memory: Agent Memory Under Partial Observability
    Junfeng Liao, Qizhou Wang, Jianing Zhu, et al. arXiv 2026. [Paper]

  38. MemFlow: Intent-Driven Memory Orchestration for Small Language Model Agents
    Jiayi Chen, Yingcong Li, Guiling Wang. arXiv 2026. [Paper]

  39. Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory
    Derong Xu, Shuochen Liu, Pengfei Luo, et al. arXiv 2026. [Paper]

  40. MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents
    Tianyu Hu, Weikai Lin, Weizhi Zhang, et al. arXiv 2026. [Paper]

  41. From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction
    Alex Petrov, Alexander Gusak, Denis Mukha, et al. arXiv 2026. [Paper]

  42. Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents
    Seyed Moein Abtahi, Rasa Rahnema, Hetkumar Patel, et al. arXiv 2026. [Paper]

  43. Gated Memory Policy
    Yihuai Gao, Jinyun Liu, Shuang Li, et al. arXiv 2026. [Paper]

  44. MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search
    Sheng Zhang, Junyi Li, Yingyi Zhang, et al. arXiv 2026. [Paper]

  45. Trust Your Memory: Verifiable Control of Smart Homes through Reinforcement Learning with Multi-dimensional Rewards
    Kai-Yuan Guo, Jiang Wang, Renjie Zhao, et al. arXiv 2026. [Paper]

  46. Constraint-Aware Corrective Memory for Language-Based Drug Discovery Agents
    Maochen Sun, Youzhi Zhang, Gaofeng Meng. arXiv 2026. [Paper]

  47. MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversation
    Jyotika Singh, Fang Tu, Miguel Ballesteros, et al. arXiv 2026. [Paper]

  48. Artifacts as Memory Beyond the Agent Boundary
    John D. Martin, Fraser Mince, Esra'a Saleh, et al. arXiv 2026. [Paper]

  49. TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation
    Xinliang Frederick Zhang, Lu Wang. arXiv 2026. [Paper]

  50. MemReader: From Passive to Active Extraction for Long-Term Agent Memory
    Jingyi Kang, Chunyu Li, Ding Chen, et al. arXiv 2026. [Paper]

  51. LightThinker++: From Reasoning Compression to Memory Management
    Yuqi Zhu, Jintian Zhang, Zhenjie Wan, et al. arXiv 2026. [Paper]

  52. SelRoute: Query-Type-Aware Routing for Long-Term Conversational Memory Retrieval
    Matthew McKee. arXiv 2026. [Paper]

  53. MemRerank: Preference Memory for Personalized Product Reranking
    Zhiyuan Peng, Xuyang Wu, Huaixiao Tou, et al. arXiv 2026. [Paper]

  54. Memento-Skills: Let Agents Design Agents
    Huichi Zhou, Siyuan Guo, Anjie Liu, et al. arXiv 2026. [Paper]

  55. SuperLocalMemory V3: Information-Geometric Foundations for Zero-LLM Enterprise Agent Memory
    Varun Pratap Bhardwaj. arXiv 2026. [Paper]

  56. Structured Distillation for Personalized Agent Memory: 11x Token Reduction with Retrieval Preservation
    Sydney Lewis. arXiv 2026. [Paper]

  57. Trajectory-Informed Memory Generation for Self-Improving Agent Systems
    Gaodan Fang, Vatche Isahagian, K. R. Jayaram, et al. arXiv 2026. [Paper]

  58. TA-Mem: Tool-Augmented Autonomous Memory Retrieval for LLM in Long-Term Conversational QA
    Mengwei Yuan, Jianan Liu, Jing Yang, et al. arXiv 2026. [Paper]

  59. MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning
    Jiejun Tan, Zhicheng Dou, Liancheng Zhang, et al. arXiv 2026. [Paper]

  60. According to Me: Long-Term Personalized Referential Memory QA
    Jingbiao Mei, Jinghong Chen, Guangyu Yang, et al. arXiv 2026. [Paper]

  61. MemPO: Self-Memory Policy Optimization for Long-Horizon Agents
    Ruoran Li, Xinghua Zhang, Haiyang Yu, et al. arXiv 2026. [Paper]

  62. Towards Autonomous Memory Agents
    Xinle Wu, Rui Zhang, Mustafa Anis Hussain, et al. arXiv 2026. [Paper]

  63. Structurally Aligned Subtask-Level Memory for Software Engineering Agents
    Kangning Shen, Jingyuan Zhang, Chenxi Sun, et al. arXiv 2026. [Paper]

  64. Hippocampus: An Efficient and Scalable Memory Module for Agentic AI
    Yi Li, Lianjie Cao, Faraz Ahmed, et al. arXiv 2026. [Paper]

  65. Scene-Aware Memory Discrimination: Deciding Which Personal Knowledge Stays
    Yijie Zhong, Mengying Guo, Zewei Wang, et al. arXiv 2026. [Paper]

  66. UMEM: Unified Memory Extraction and Management Framework for Generalizable Memory
    Yongshi Ye, Hui Jiang, Feihu Jiang, et al. arXiv 2026. [Paper]

  67. AMEM4Rec: Leveraging Cross-User Similarity for Memory Evolution in Agentic LLM Recommenders
    Minh-Duc Nguyen, Hai-Dang Kieu, Dung D. Le. arXiv 2026. [Paper]

  68. Learning to Continually Learn via Meta-learning Agentic Memory Designs
    Yiming Xiong, Shengran Hu, Jeff Clune. arXiv 2026. [Paper]

  69. Learning to Share: Selective Memory for Efficient Parallel Agentic Systems
    Joseph Fioresi, Parth Parag Kulkarni, Ashmal Vayani, et al. arXiv 2026. [Paper]

  70. MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
    Haozhen Zhang, Quanyu Long, Jianzhu Bao, et al. arXiv 2026. [Paper]

  71. Live-Evo: Online Evolution of Agentic Memory from Continuous Feedback
    Yaolun Zhang, Yiran Wu, Yijiong Yu, et al. arXiv 2026. [Paper]

  72. Darwinian Memory: A Training-Free Self-Regulating Memory System for GUI Agent Evolution
    Hongze Mi, Yibo Feng, WenJie Lu, et al. arXiv 2026. [Paper]

  73. MAGNET: Towards Adaptive GUI Agents with Memory-Driven Knowledge Evolution
    Libo Sun, Jiwen Zhang, Siyuan Wang, et al. arXiv 2026. [Paper]

  74. Dep-Search: Learning Dependency-Aware Reasoning Traces with Persistent Memory
    Yanming Liu, Xinyue Peng, Zixuan Yan, et al. arXiv 2026. [Paper]

  75. Clustering-driven Memory Compression for On-device Large Language Models
    Ondrej Bohdal, Pramit Saha, Umberto Michieli, et al. arXiv 2026. [Paper]

  76. Chain-of-Memory: Lightweight Memory Construction with Dynamic Evolution for LLM Agents
    Xiucheng Xu, Bingbing Xu, Xueyun Tian, et al. arXiv 2026. [Paper]

  77. LLM-as-RNN: A Recurrent Language Model for Memory Updates and Sequence Prediction
    Yuxing Lu, J. Ben Tamo, Weichen Zhao, et al. arXiv 2026. [Paper]

  78. Grounding Agent Memory in Contextual Intent
    Ruozhen Yang, Yucheng Jiang, Yueqi Jiang, et al. arXiv 2026. [Paper]

  79. Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Management
    Weitao Ma, Xiaocheng Feng, Lei Huang, et al. arXiv 2026. [Paper]

  80. AtomMem : Learnable Dynamic Agentic Memory with Atomic Memory Operation
    Yupeng Huo, Yaxi Lu, Zhong Zhang, et al. arXiv 2026. [Paper]

  81. Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents
    Miao Su, Yucan Guo, Zhongni Hou, et al. arXiv 2026. [Paper]

  82. Active Context Compression: Autonomous Memory Management in LLM Agents
    Nikhil Verma. arXiv 2026. [Paper]

  83. MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences
    Qihao Wang, Ziming Cheng, Shuo Zhang, et al. arXiv 2026. [Paper]

  84. MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewards
    Zhiyu Shen, Ziming Wu, Fuming Lai, et al. arXiv 2026. [Paper]

  85. Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoning
    Yuyang Hu, Jiongnan Liu, Jiejun Tan, et al. arXiv 2026. [Paper]

  86. Beyond Static Summarization: Proactive Memory Extraction for LLM Agents
    Chengyuan Yang, Zequn Sun, Wei Wei, et al. arXiv 2026. [Paper]

  87. MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
    Shengtao Zhang, Jiaqian Wang, Ruiwen Zhou, et al. arXiv 2026. [Paper]

  88. CodeMEM: AST-Guided Adaptive Memory for Repository-Level Iterative Code Generation
    Peiding Wang, Li Zhang, Fang Liu, et al. arXiv 2026. [Paper]

  89. SimpleMem: Efficient Lifelong Memory for LLM Agents
    Jiaqi Liu, Yaofeng Su, Peng Xia, et al. arXiv 2026. [Paper]

  90. PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agents
    Namyoung Kim, Kai Tzu-iunn Ong, Yeonjun Hwang, et al. EMNLP 2025. [Paper]

  91. Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialogue
    Sangyeop Kim, Yohan Lee, Sanghwa Kim, et al. EMNLP 2025. [Paper]

  92. Contextual Experience Replay for Self-Improvement of Language Agents
    Yitao Liu, Chenglei Si, Karthik Narasimhan, et al. ACL 2025. [Paper]

  93. In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents
    Zhen Tan, Jun Yan, I-Hung Hsu, et al. ACL 2025. [Paper]

  94. Improving Factuality with Explicit Working Memory
    Mingda Chen, Yang Li, Karthik Padthe, et al. ACL 2025. [Paper]

  95. Agent Workflow Memory
    Zora Zhiruo Wang, Jiayuan Mao, Daniel Fried, Graham Neubig. ICML 2025. [Paper] [Code]

  96. Human-inspired Episodic Memory for Infinite Context LLMs
    Zafeirios Fountas, Martin A Benfeghoul, Adnan Oomerjee, et al. ICLR 2025. [Paper]

  97. Towards Lifelong Dialogue Agents via Timeline-based Memory Management
    Kai Tzu-iunn Ong, Namyoung Kim, Minju Gwak, et al. NAACL 2025. [Paper]

  98. Hello Again! LLM-powered Personalized Agent for Long-term Dialogue
    Hao Li, Chenghao Yang, An Zhang, et al. NAACL 2025. [Paper]

  99. Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations
    Nuo Chen, Hongguang Li, Juhua Huang, et al. COLING 2025. [Paper] [Code]

  100. Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models
    Qingyue Wang, Yanhe Fu, Yanan Cao, et al. Neurocomputing 2025. [Paper]

  101. SCM: Enhancing Large Language Model with Self-Controlled Memory Framework
    Bing Wang, Xinnian Liang, Jian Yang, et al. DASFAA 2025. [Paper]

  102. Verbatim Chunks Beat Extracted Artifacts: A Controlled Ablation of Memory Representations for Long LLM Conversations
    Tao An. arXiv 2025. [Paper]

  103. Memento 2: Learning by Stateful Reflective Memory
    Jun Wang. arXiv 2025. [Paper]

  104. MemR³: Memory Retrieval via Reflective Reasoning for LLM Agents
    Xingbo Du, Loka Li, Duzhen Zhang, et al. arXiv 2025. [Paper]

  105. ABBEL: Learning Natural-Language Belief States for Memory-Efficient Interaction
    Aly Lidayan, Jakob Bjorner, Satvik Golechha, et al. arXiv 2025. [Paper]

  106. Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents
    Yiming Du, Baojun Wang, Yifan Xiang, et al. arXiv 2025. [Paper]

  107. Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
    Zouying Cao, Jiaji Deng, Li Yu, et al. arXiv 2025. [Paper]

  108. LightSearcher: Efficient DeepSearch via Experiential Memory
    Hengzhi Lan, Yue Yu, Li Qian, et al. arXiv 2025. [Paper]

  109. Solving Context Window Overflow in AI Agents
    Anton Bulle Labate, Valesca Moura de Sousa, Sandro Rama Fiorini, et al. arXiv 2025. [Paper]

  110. Goal-Directed Search Outperforms Goal-Agnostic Memory Compression in Long-Context Memory Tasks
    Yicong Zheng, Kevin L. McKee, Thomas Miconi, et al. arXiv 2025. [Paper]

  111. Improving Language Agents through BREW: Bootstrapping expeRientially-learned Environmental knoWledge
    Shashank Kirtania, Param Biyani, Priyanshu Gupta, et al. arXiv 2025. [Paper]

  112. Episodic Memory in Agentic Frameworks: Suggesting Next Tasks
    Sandro Rama Fiorini, Leonardo G. Azevedo, Raphael M. Thiago, et al. arXiv 2025. [Paper]

  113. A Simple Yet Strong Baseline for Long-Term Conversational Memory of LLM Agents
    Sizhe Zhou, Jiawei Han. arXiv 2025. [Paper]

  114. WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidance
    Genglin Liu, Shijie Geng, Sha Li, et al. arXiv 2025. [Paper]

  115. Experience-Guided Adaptation of Inference-Time Reasoning Strategies
    Adam Stein, Matthew Trager, Benjamin Bowman, et al. arXiv 2025. [Paper]

  116. Smarter Together: Creating Agentic Communities of Practice through Shared Experiential Learning
    Valentin Tablan, Scott Taylor, Gabriel Hurtado, et al. arXiv 2025. [Paper]

  117. Efficient On-Device Agents via Adaptive Context Management
    Sanidhya Vijayvargiya, Rahul Lokesh. arXiv 2025. [Paper]

  118. Dynamic Affective Memory Management for Personalized LLM Agents
    Junfeng Lu, Yueyan Li. arXiv 2025. [Paper]

  119. AgentFold: Long-Horizon Web Agents with Proactive Context Management
    Rui Ye, Zhongwang Zhang, Kuan Li, et al. arXiv 2025. [Paper]

  120. Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks
    Yuxiang Zhang, Jiangming Shu, Ye Ma, et al. arXiv 2025. [Paper]

  121. Preference-Aware Memory Update for Long-Term LLM Agents
    Haoran Sun, Zekun Zhang, Shaoning Zeng. arXiv 2025. [Paper]

  122. Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profiles
    Rebecca Westhäußer, Wolfgang Minker, Sebatian Zepf. arXiv 2025. [Paper]

  123. Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
    Miao Lu, Weiwei Sun, Weihua Du, et al. arXiv 2025. [Paper]

  124. Improving Code Localization with Repository Memory
    Boshi Wang, Weijian Xu, Yunsheng Li, et al. arXiv 2025. [Paper]

  125. ACON: Optimizing Context Compression for Long-horizon LLM Agents
    Minki Kang, Wei-Ning Chen, Dongge Han, et al. arXiv 2025. [Paper]

  126. Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents
    Yaorui Shi, Yuxin Chen, Siyuan Wang, et al. arXiv 2025. [Paper]

  127. ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization
    Xixi Wu, Kuan Li, Yida Zhao, et al. arXiv 2025. [Paper]

  128. ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory
    Matthew Ho, Chen Si, Zhaoxiang Feng, et al. arXiv 2025. [Paper]

  129. Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
    Sikuan Yan, Xiufeng Yang, Zuchao Huang, et al. arXiv 2025. [Paper]

  130. Learn to Memorize: Optimizing LLM-based Agents with Adaptive Memory Framework
    Zeyu Zhang, Quanyu Dai, Rui Li, et al. arXiv 2025. [Paper]

  131. Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
    Huichi Zhou, Yihang Chen, Siyuan Guo, et al. arXiv 2025. [Paper]

  132. Semantic Anchoring in Agentic Memory: Leveraging Linguistic Structures for Persistent Conversational Context
    Maitreyi Chatterjee, Devansh Agarwal. arXiv 2025. [Paper]

  133. Memp: Exploring Agent Procedural Memory
    Runnan Fang, Yuan Liang, Xiaobin Wang, et al. arXiv 2025. [Paper]

  134. Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management
    Mo Li, L. H. Xu, Qitai Tan, et al. arXiv 2025. [Paper]

  135. SWE-Exp: Experience-Driven Software Issue Resolution
    Silin Chen, Shaoxin Lin, Yuling Shi, et al. arXiv 2025. [Paper]

  136. MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversations
    Elias Lumer, Anmol Gulati, Vamse Kumar Subbiah, et al. arXiv 2025. [Paper]

  137. Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving
    Xiangru Tang, Tianrui Qin, Tianhao Peng, et al. arXiv 2025. [Paper]

  138. Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents
    Qizheng Zhang, Michael Wornow, Gerry Wan, et al. arXiv 2025. [Paper]

  139. MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents
    Yiming Du, Bingbing Wang, Yang He, et al. arXiv 2025. [Paper]

  140. Task-Core Memory Management and Consolidation for Long-term Continual Learning
    Tianyu Huai, Jie Zhou, Yuxuan Cai, et al. arXiv 2025. [Paper]

  141. Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory
    Mirac Suzgun, Mert Yuksekgonul, Federico Bianchi, et al. arXiv 2025. [Paper]

  142. MemInsight: Autonomous Memory Augmentation for LLM Agents
    Rana Salama, Jason Cai, Michelle Yuan, et al. arXiv 2025. [Paper]

  143. Memory-augmented Query Reconstruction for LLM-based Knowledge Graph Reasoning
    Mufan Xu, Gewen Liang, Kehai Chen, et al. arXiv 2025. [Paper]

  144. Interpersonal Memory Matters: A New Task for Proactive Dialogue Utilizing Conversational History
    Bowen Wu, Wenqing Wang, Haoran Li, et al. arXiv 2025. [Paper]

  145. On Memory Construction and Retrieval for Personalized Conversational Agents
    Zhuoshi Pan, Qianhui Wu, Huiqiang Jiang, et al. arXiv 2025. [Paper]

  146. Wormhole Memory: A Rubik's Cube for Cross-Dialogue Retrieval
    Libo Wang. arXiv 2025. [Paper]

  147. "My agent understands me better": Integrating Dynamic Human-like Memory Recall and Consolidation in LLM-Based Agents
    Yuki Hou, Haruki Tamoto, Homei Miyashita. CHI 2024 Extended Abstracts. [Paper]

  148. ExpeL: LLM Agents Are Experiential Learners
    Andrew Zhao, Daniel Huang, Quentin Xu, et al. AAAI 2024. [Paper] [Code]

  149. MemoryBank: Enhancing Large Language Models with Long-Term Memory
    Wanjun Zhong, Lianghong Guo, Qiqi Gao, et al. AAAI 2024. [Paper] [Code]

  150. Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control
    Longtao Zheng, Rundong Wang, Xinrun Wang, Bo An. ICLR 2024. [Paper] [Code]

  151. Self-evolving Agents with reflective and memory-augmented abilities
    Xuechen Liang, Yangfan He, Yinghui Xia, et al. arXiv 2024. [Paper]

  152. Generative Agents: Interactive Simulacra of Human Behavior
    Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai, et al. UIST 2023. [Paper] [Code]

  153. MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation
    Junru Lu, Siyu An, Mingbao Lin, et al. arXiv 2023. [Paper] [Code]

  154. RET-LLM: Towards a General Read-Write Memory for Large Language Models
    Ali Modarressi, Ayyoob Imani, Mohsen Fayyaz, Hinrich Schütze. arXiv 2023. [Paper]

⬆️ top

1.1.2 Parameter and Latent Memory

Memory stored in model parameters, learned memory modules, hidden states, attention key-values, or other continuous latent representations.

  1. TokMem: One-Token Procedural Memory for Large Language Models
    Zijun Wu, Yongchang Hao, Lili Mou. ICLR 2026. [Paper]

  2. MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents
    Zijian Zhou, Ao Qu, Zhaoxuan Wu, et al. ICLR 2026. [Paper] [Code]

  3. User as Engram: Internalizing Per-User Memory as Local Parametric Edits
    Bojie Li. arXiv 2026. [Paper]

  4. Scaling Self-Evolving Agents via Parametric Memory
    Tao Ren, Weiyao Luo, Hui Yang, et al. arXiv 2026. [Paper]

  5. Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories
    Ali Behrouz, Farnoosh Hashemi, Adel Javanmard, et al. arXiv 2026. [Paper]

  6. Do Language Models Need Sleep? Offline Recurrence for Improved Online Inference
    Sangyun Lee, Sean McLeish, Tom Goldstein, et al. arXiv 2026. [Paper]

  7. MeMo: Memory as a Model
    Ryan Wei Heng Quek, Sanghyuk Lee, Alfred Wei Lun Leong, et al. arXiv 2026. [Paper]

  8. δ-mem: Efficient Online Memory for Large Language Models
    Jingdi Lei, Di Zhang, Junxian Li, et al. arXiv 2026. [Paper]

  9. GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent
    Yuri Kuratov, Matvey Kairov, Aydar Bulatov, et al. arXiv 2026. [Paper]

  10. Memory Caching: RNNs with Growing Memory
    Ali Behrouz, Zeman Li, Yuan Deng, et al. arXiv 2026. [Paper]

  11. ParamMem: Augmenting Language Agents with Parametric Reflective Memory
    Tianjun Yao, Yongqiang Chen, Yujia Zheng, et al. arXiv 2026. [Paper]

  12. Tell Me What To Learn: Generalizing Neural Memory to be Controllable in Natural Language
    Max S. Bennett, Thomas P. Zollo, Richard Zemel. arXiv 2026. [Paper]

  13. Field-Theoretic Memory for AI Agents: Continuous Dynamics for Context Preservation
    Subhadip Mitra. arXiv 2026. [Paper]

  14. Language Model Memory and Memory Models for Language
    Benjamin L. Badger. arXiv 2026. [Paper]

  15. Learning to Forget Attention: Memory Consolidation for Adaptive Compute Reduction
    Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma. arXiv 2026. [Paper]

  16. Towards Compressive and Scalable Recurrent Memory
    Yunchong Song, Jushi Kai, Liming Lu, et al. arXiv 2026. [Paper]

  17. When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning
    Leheng Sheng, Yongtao Zhang, Wenchang Ma, et al. arXiv 2026. [Paper]

  18. MeKi: Memory-based Expert Knowledge Injection for Efficient LLM Scaling
    Ning Ding, Fangcheng Liu, Kyungrae Kim, et al. arXiv 2026. [Paper]

  19. A Collision-Free Hot-Tier Extension for Engram-Style Conditional Memory: A Controlled Study of Training Dynamics
    Tao Lin. arXiv 2026. [Paper]

  20. Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
    Xin Cheng, Rui Tian, Wangding Zeng, et al. arXiv 2026. [Paper]

  21. Fast-weight Product Key Memory
    Tianyu Zhao, Llion Jones. arXiv 2026. [Paper]

  22. Nested Learning: The Illusion of Deep Learning Architectures
    Ali Behrouz, Meisam Razaviyayn, Peilin Zhong, et al. NeurIPS 2025. [Paper]

  23. EpMAN: Episodic Memory AttentioN for Generalizing to Longer Contexts
    Subhajit Chaudhury, Payel Das, Sarathkrishna Swaminathan, et al. ACL 2025. [Paper]

  24. Ultra-Sparse Memory Network
    Zihao Huang, Qiyang Min, Hongzhi Huang, et al. ICLR 2025. [Paper]

  25. Self-Updatable Large Language Models by Integrating Context into Model Parameters
    Yu Wang, Xinshuang Liu, Xiusi Chen, et al. ICLR 2025. [Paper]

  26. MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation
    Hongjin Qian, Zheng Liu, Peitian Zhang, et al. WWW 2025. [Paper] [Code]

  27. MemLoRA: Distilling Expert Adapters for On-Device Memory Systems
    Massimo Bini, Ondrej Bohdal, Umberto Michieli, et al. arXiv 2025. [Paper]

  28. VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models
    Xinlei Yu, Chengming Xu, Guibin Zhang, et al. arXiv 2025. [Paper]

  29. Continual Learning via Sparse Memory Finetuning
    Jessy Lin, Luke Zettlemoyer, Gargi Ghosh, et al. arXiv 2025. [Paper]

  30. Auto-scaling Continuous Memory for GUI Agent
    Wenyi Wu, Kun Zhou, Ruoxin Yuan, et al. arXiv 2025. [Paper]

  31. Memory Retrieval and Consolidation in Large Language Models through Function Tokens
    Shaohua Zhang, Yuan Lin, Hang Li. arXiv 2025. [Paper]

  32. Pretraining with hierarchical memories: separating long-tail and common knowledge
    Hadi Pouransari, David Grangier, C Thomas, et al. arXiv 2025. [Paper]

  33. MemGen: Weaving Generative Latent Memory for Self-Evolving Agents
    Guibin Zhang, Muxin Fu, Shuicheng Yan. arXiv 2025. [Paper]

  34. MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation
    Hao Shi, Bin Xie, Yingfei Liu, et al. arXiv 2025. [Paper]

  35. Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models
    Jiaqi Cao, Jiarui Wang, Rubin Wei, et al. arXiv 2025. [Paper]

  36. MLP Memory: A Retriever-Pretrained Memory for Large Language Models
    Rubin Wei, Jiaqi Cao, Jiarui Wang, et al. arXiv 2025. [Paper]

  37. Towards General Continuous Memory for Vision-Language Models
    Wenyi Wu, Zixuan Song, Kun Zhou, et al. arXiv 2025. [Paper]

  38. Memorization and Knowledge Injection in Gated LLMs
    Xu Pan, Ely Hahami, Zechen Zhang, et al. arXiv 2025. [Paper]

  39. Echo: A Large Language Model with Temporal Episodic Memory
    WenTao Liu, Ruohua Zhang, Aimin Zhou, et al. arXiv 2025. [Paper]

  40. R³Mem: Bridging Memory Retention and Retrieval via Reversible Compression
    Xiaoqiang Wang, Suyuchen Wang, Yun Zhu, et al. arXiv 2025. [Paper]

  41. MoM: Linear Sequence Modeling with Mixture-of-Memories
    Jusen Du, Weigao Sun, Disen Lan, et al. arXiv 2025. [Paper]

  42. LM2: Large Memory Models
    Jikun Kang, Wenqi Wu, Filippos Christianos, et al. arXiv 2025. [Paper]

  43. M+: Extending MemoryLLM with Scalable Long-Term Memory
    Yu Wang, Dmitry Krotov, Yuanzhe Hu, et al. arXiv 2025. [Paper]

  44. Memory³: Language Modeling with Explicit Memory
    Hongkang Yang, Zehao Lin, Wenjin Wang, et al. Journal of Machine Learning 2024. [Paper]

  45. WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
    Peng Wang, Zexi Li, Ningyu Zhang, et al. NeurIPS 2024. [Paper] [Code]

  46. Online Adaptation of Language Models with a Memory of Amortized Contexts
    Jihoon Tack, Jaehyung Kim, Eric Mitchell, et al. NeurIPS 2024. [Paper] [Code]

  47. InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
    Chaojun Xiao, Pengle Zhang, Xu Han, et al. NeurIPS 2024. [Paper] [Code]

  48. MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
    Bo He, Hengduo Li, Young Kyun Jang, et al. CVPR 2024. [Paper] [Code]

  49. Larimar: Large Language Models with Episodic Memory Control
    Payel Das, Subhajit Chaudhury, Elliot Nelson, et al. ICML 2024. [Paper] [Code]

  50. MEMORYLLM: Towards Self-Updatable Large Language Models
    Yu Wang, Yifan Gao, Xiusi Chen, et al. ICML 2024. [Paper] [Code]

  51. Compressed Context Memory for Online Language Model Interaction
    Jang-Hyun Kim, Junyoung Yeom, Sangdoo Yun, Hyun Oh Song. ICLR 2024. [Paper] [Code]

  52. Efficient Streaming Language Models with Attention Sinks
    Guangxuan Xiao, Yuandong Tian, Beidi Chen, et al. ICLR 2024. [Paper] [Code]

  53. Titans: Learning to Memorize at Test Time
    Ali Behrouz, Peilin Zhong, Vahab Mirrokni. arXiv 2024. [Paper]

  54. Augmenting Language Models with Long-Term Memory
    Weizhi Wang, Li Dong, Hao Cheng, et al. NeurIPS 2023. [Paper] [Code]

  55. Memorizing Transformers
    Yuhuai Wu, Markus N. Rabe, DeLesley Hutchins, Christian Szegedy. ICLR 2022 Spotlight. [Paper]

⬆️ top

1.2 Structured Topological Memory Systems

1.2.1 Graph-Based Memory

Memory organized as entities, relations, notes, events, or episodes connected by explicit graph edges.

  1. Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents
    Shuo Ji, Yibo Li, Bryan Hooi. ICML 2026. [Paper]

  2. GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs
    Tao Feng, Haozhen Zhang, Zijie Lei, et al. ICLR 2026. [Paper]

  3. REMem: Reasoning with Episodic Memory in Language Agent
    Yiheng Shu, Saisri Padmaja Jonnalagedda, Xiang Gao, et al. ICLR 2026. [Paper]

  4. MIRA: Memory-Integrated Reinforcement Learning Agent with Limited LLM Guidance
    Narjes Nourzad, Carlee Joe-Wong. ICLR 2026. [Paper]

  5. MemRec: Collaborative Memory-Augmented Agentic Recommender System
    Weixin Chen, Yuhan Zhao, Jingyuan Huang, et al. ACL 2026. [Paper]

  6. LOOM: Personalized Learning Informed by Daily LLM Conversations Toward Long-Term Mastery via a Dynamic Learner Memory Graph
    Justin Cui, Kevin Pu, Tovi Grossman. AAAI 2026. [Paper]

  7. MemoTime: Memory-Augmented Temporal Knowledge Graph Enhanced Large Language Model Reasoning
    Xingyu Tan, Xiaoyang Wang, Qing Liu, et al. WWW 2026. [Paper]

  8. DYNA : Dynamic Episodic Memory Networks for Augmenting Large Language Models with Temporal Knowledge Graphs in Continuous Learning
    Ali Sarabadani, Mahtab Tajvidiyan. arXiv 2026. [Paper]

  9. GitOfThoughts: Version-Controlled Reasoning and Agent Memory You Can Replay, Diff, and Merge
    Pavan C Shekar, Abhishek H S, Aswanth Krishnan. arXiv 2026. [Paper]

  10. G-Long: Graph-Enhanced Memory Management for Efficient Long-Term Dialogue Agents
    Minjun Choi, Yoonjin Jang, Sangwon Youn, et al. arXiv 2026. [Paper]

  11. Trace Only What You Need: Structure-Aware On-Demand Hypergraph Memory for Long-Document Question Answering
    Xiangjun Zai, Xingyu Tan, Chen Chen, et al. arXiv 2026. [Paper]

  12. REAL: A Reasoning-Enhanced Graph Framework for Long-Term Memory Management of LLMs
    Keer Lu, Liwei Chen, Guoqing Jiang, et al. arXiv 2026. [Paper]

  13. TokenMizer: Graph-Structured Session Memory for Long-Horizon LLM Context Management
    Shweta Mishra. arXiv 2026. [Paper]

  14. SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory
    Juntong Wang, Haoyue Zhao, guanghui Pan, et al. arXiv 2026. [Paper]

  15. The Dynamic Gist-Based Memory Model (DGMM): A Memory-Centric Architecture for Artificial Intelligence
    Terry Dorsey, Kevin Huggins. arXiv 2026. [Paper]

  16. MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents
    Hung Pham Van, Nguyen Manh Hieu, Khang Pham Tran Tuan, et al. arXiv 2026. [Paper]

  17. CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning
    Cheng-Yen Li, Xuanjun Chen, Claire Lin, et al. arXiv 2026. [Paper]

  18. HyperMem: Hypergraph Memory for Long-Term Conversations
    Juwei Yue, Chuanrui Hu, Jiawei Sheng, et al. arXiv 2026. [Paper]

  19. Task-Adaptive Retrieval over Agentic Multi-Modal Web Histories via Learned Graph Memory
    Saman Forouzandeh, Kamal Berahmand, Mahdi Jalili. arXiv 2026. [Paper]

  20. Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP
    Martin Vogel, Falk Meyer-Eschenbach, Severin Kohler, et al. arXiv 2026. [Paper]

  21. PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents
    Ke Yang, Zixi Chen, Xuan He, et al. arXiv 2026. [Paper]

  22. Understand Then Memory: A Cognitive Gist-Driven RAG Framework with Global Semantic Diffusion
    Pengcheng Zhou, Haochen Li, Zhiqiang Nie, et al. arXiv 2026. [Paper]

  23. Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory
    Zihao Tang, Xin Yu, Ziyu Xiao, et al. arXiv 2026. [Paper]

  24. MemAdapter: Fast Alignment across Agent Memory Paradigms via Generative Subgraph Retrieval
    Xin Zhang, Kailai Yang, Chenyue Li, et al. arXiv 2026. [Paper]

  25. Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
    Menglin Xia, Xuchao Zhang, Shantanu Dixit, et al. arXiv 2026. [Paper]

  26. SwiftMem: Fast Agentic Memory via Query-aware Indexing
    Anxin Tian, Yiming Li, Xing Li, et al. arXiv 2026. [Paper]

  27. MemoBrain: Executive Memory as an Agentic Brain for Reasoning
    Hongjin Qian, Zhao Cao, Zheng Liu. arXiv 2026. [Paper]

  28. Implicit Graph, Explicit Retrieval: Towards Efficient and Interpretable Long-horizon Memory for Large Language Models
    Xin Zhang, Kailai Yang, Hao Li, et al. arXiv 2026. [Paper]

  29. MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents
    Dongming Jiang, Yi Li, Guanpeng Li, et al. arXiv 2026. [Paper]

  30. SYNAPSE: Empowering LLM Agents with Episodic-Semantic Memory via Spreading Activation
    Hanqi Jiang, Junhao Chen, Yi Pan, et al. arXiv 2026. [Paper]

  31. Bridging Intuitive Associations and Deliberate Recall: Empowering LLM Personal Assistant with Graph-Structured Long-term Memory
    Yujie Zhang, Weikang Yuan, Zhuoren Jiang. Findings of ACL 2025. [Paper]

  32. SynapticRAG: Enhancing Temporal Memory Retrieval in Large Language Models through Synaptic Mechanisms
    Yuki Hou, Haruki Tamoto, Qinghua Zhao, et al. Findings of ACL 2025. [Paper]

  33. From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
    Bernal Jiménez Gutiérrez, Yiheng Shu, Weijian Qi, et al. ICML 2025. [Paper] [Code]

  34. A-MEM: Agentic Memory for LLM Agents
    Wujiang Xu, Zujie Liang, Kai Mei, et al. NeurIPS 2025. [Paper] [Code]

  35. AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents
    Petr Anokhin, Nikita Semenov, Artyom Sorokin, et al. IJCAI 2025. [Paper] [Code]

  36. MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory
    Ali Modarressi, Abdullatif Köksal, Ayyoob Imani, et al. TMLR 2025. [Paper] [Code]

  37. Describe Anything Anywhere At Any Moment
    Nicolas Gorlo, Lukas Schmid, Luca Carlone. arXiv 2025. [Paper]

  38. From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory
    Siyu Xia, Zekun Xu, Jiajun Chai, et al. arXiv 2025. [Paper]

  39. MemoriesDB: A Temporal-Semantic-Relational Database for Long-Term Agent Memory / Modeling Experience as a Graph of Temporal-Semantic Surfaces
    Joel Ward. arXiv 2025. [Paper]

  40. LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning
    Zhengjun Huang, Zhoujin Tian, Qintian Guo, et al. arXiv 2025. [Paper]

  41. AssoMem: Scalable Memory QA with Multi-Signal Associative Retrieval
    Kai Zhang, Xinyuan Zhang, Ejaz Ahmed, et al. arXiv 2025. [Paper]

  42. Mnemosyne: An Unsupervised, Human-Inspired Long-Term Memory Architecture for Edge-Based LLMs
    Aneesh Jonelagadda, Christina Hahn, Haoze Zheng, et al. arXiv 2025. [Paper]

  43. SGMem: Sentence Graph Memory for Long-Term Conversational Agents
    Yaxiong Wu, Yongyue Zhang, Sheng Liang, et al. arXiv 2025. [Paper]

  44. Cognitive Weave: Synthesizing Abstracted Knowledge with a Spatio-Temporal Resonance Graph
    Akash Vishwakarma, Hojin Lee, Mohith Suresh, et al. arXiv 2025. [Paper]

  45. LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning
    Hanqing Yang, Jingdi Chen, Marie Siew, et al. arXiv 2025. [Paper]

  46. Zep: A Temporal Knowledge Graph Architecture for Agent Memory
    Preston Rasmussen, Pavlo Paliychuk, Travis Beauvais, Jack Ryan, Daniel Chalef. arXiv 2025. [Paper] [Code]

  47. Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory Graphs
    Zheng Wang, Zhongyang Li, Zeren Jiang, et al. EMNLP 2024. [Paper]

  48. HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
    Bernal Jiménez Gutiérrez, Yiheng Shu, Yu Gu, et al. NeurIPS 2024. [Paper] [Code] [Dataset]

  49. On the Structural Memory of LLM Agents
    Ruihong Zeng, Jinyuan Fang, Siwei Liu, Zaiqiao Meng. arXiv 2024. [Paper]

⬆️ top

1.2.2 Hierarchical Memory

Memory organized across levels, layers, trees, subgoals, or progressively abstracted summaries.

  1. SE-GA: Memory-Augmented Self-Evolution for GUI Agents
    Shilong Jin, Lanjun Wang, Zhuosheng Zhang. ICML 2026. [Paper]

  2. RGMem: Renormalization Group-inspired Memory Evolution for Language Agents
    Ao Tian, Yunfeng Lu, Xinxin Fan, et al. ICML 2026. [Paper]

  3. Hierarchical Long-Term Semantic Memory for LinkedIn's Hiring Agent
    Zhentao Xu, Shangjin Zhang, Emir Poyraz, et al. KDD 2026. [Paper]

  4. HiGMem: A Hierarchical and LLM-Guided Memory System for Long-Term Conversational Agents
    Shuqi Cao, Jingyi He, Fei Tan. ACL 2026. [Paper]

  5. OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning
    Zhijia Liang, Jiaming Li, Weikai Chen, et al. CVPR 2026. [Paper]

  6. VideoARM: Agentic Reasoning over Hierarchical Memory for Long-Form Video Understanding
    Yufei Yin, Qianke Meng, Minghao Chen, et al. CVPR 2026. [Paper]

  7. Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction
    Zhaopei Huang, Qifeng Dai, Guozheng Wu, et al. AAAI 2026. [Paper]

  8. MemWeaver: A Hierarchical Memory from Textual Interactive Behaviors for Personalized Generation
    Shuo Yu, Mingyue Cheng, Daoyu Wang, et al. WWW 2026. [Paper]

  9. MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision
    Ye Jin, Yangyang Xu, Jun Zhu, et al. arXiv 2026. [Paper]

  10. Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents
    Hao-Lun Hsu, Nikki Lijing Kuang, Boyi Liu, et al. arXiv 2026. [Paper]

  11. Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents
    Yaoqi Chen, Haibin Lai, Yuru Feng, et al. arXiv 2026. [Paper]

  12. PersonaTree: Structured Lifecycle Memory for Person Understanding in LLM Agents
    Yubo Hou, Jingwei Song, Hongbo Zhang, et al. arXiv 2026. [Paper]

  13. Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents
    Yifan Simon Liu, Liam Gallagher, Faeze Moradi Kalarde, et al. arXiv 2026. [Paper]

  14. DELTAMEM: Incremental Experience Memory for LLM Agents via Residual Trees
    Haoran Tan, Zeyu Zhang, Zhicheng Cao, et al. arXiv 2026. [Paper]

  15. Visual Agentic Memory: Enabling Online Long Video Understanding via Online Indexing, Hierarchical Memory, and Agentic Retrieval
    Aiden Yiliu Li, Nels Numan, Anthony Steed. arXiv 2026. [Paper]

  16. Tree-based Credit Assignment for Multi-Agent Memory System
    Marina Mao, Alexandr Liu, Pengbo Li, et al. arXiv 2026. [Paper]

  17. MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents
    Bronislav Sidik, Lior Rokach. arXiv 2026. [Paper]

  18. EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory
    Yuyang Li, Yime He, Zeyu Zhang, et al. arXiv 2026. [Paper]

  19. Retention Consequence in Lifecycle Memory Control
    Jiarui Han. arXiv 2026. [Paper]

  20. Learning to Forget -- Hierarchical Episodic Memory for Lifelong Robot Deployment
    Leonard Bärmann, Joana Plewnia, Alex Waibel, et al. arXiv 2026. [Paper]

  21. ByteRover: Agent-Native Memory Through LLM-Curated Hierarchical Context
    Andy Nguyen, Danh Doan, Hoang Pham, et al. arXiv 2026. [Paper]

  22. Oblivion: Self-Adaptive Agentic Memory Control through Decay-Driven Activation
    Ashish Rana, Chia-Chien Hung, Qumeng Sun, et al. arXiv 2026. [Paper]

  23. GAM-RAG: Gain-Adaptive Memory for Evolving Retrieval in Retrieval-Augmented Generation
    Yifan Wang, Mingxuan Jiang, Zhihao Sun, et al. arXiv 2026. [Paper]

  24. Pancake: Hierarchical Memory System for Multi-Agent LLM Serving
    Zhengding Hu, Zaifeng Pan, Prabhleen Kaur, et al. arXiv 2026. [Paper]

  25. EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use
    Siwei Wen, Zhangcheng Wang, Xingjian Zhang, et al. arXiv 2026. [Paper]

  26. TraceMem: Weaving Narrative Memory Schemata from User Conversational Traces
    Yiming Shu, Pei Liu, Tiange Zhang, et al. arXiv 2026. [Paper]

  27. Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation
    Zhanghao Hu, Qinglin Zhu, Runcong Zhao, et al. arXiv 2026. [Paper]

  28. Mem-T: Densifying Rewards for Long-Horizon Memory Agents
    Yanwei Yue, Boci Peng, Xuanbo Fan, et al. arXiv 2026. [Paper]

  29. ShardMemo: Masked MoE Routing for Sharded Agentic LLM Memory
    Yang Zhao, Chengxiao Dai, Yue Xiu, et al. arXiv 2026. [Paper]

  30. Me-Agent: A Personalized Mobile Agent with Two-Level User Habit Learning for Enhanced Interaction
    Shuoxin Wang, Chang Liu, Gowen Loo, et al. arXiv 2026. [Paper]

  31. FadeMem: Biologically-Inspired Forgetting for Efficient Agent Memory
    Lei Wei, Xiao Peng, Xu Dong, et al. arXiv 2026. [Paper]

  32. PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records
    Yibo Lyu, Gongwei Chen, Rui Shao, et al. arXiv 2026. [Paper]

  33. Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory
    Sirui Liang, Pengfei Cao, Jian Zhao, et al. arXiv 2026. [Paper]

  34. Bi-Mem: Bidirectional Construction of Hierarchical Memory for Personalized LLMs via Inductive-Reflective Agents
    Wenyu Mao, Haosong Tan, Shuchang Liu, et al. arXiv 2026. [Paper]

  35. HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agents
    Ningning Zhang, Xingxing Yang, Zhizhong Tan, et al. arXiv 2026. [Paper]

  36. Inside Out: Evolving User-Centric Core Memory Trees for Long-Term Personalized Dialogue Systems
    Jihao Zhao, Ding Chen, Zhaoxin Fan, et al. arXiv 2026. [Paper]

  37. Membox: Weaving Topic Continuity into Long-Range Memory for LLM Agents
    Dehao Tao, Guoliang Ma, Yongfeng Huang, et al. arXiv 2026. [Paper]

  38. TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents
    Kai Li, Xuanqing Yu, Ziyi Ni, et al. arXiv 2026. [Paper]

  39. CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension
    Rui Li, Zeyu Zhang, Xiaohe Bo, et al. NeurIPS 2025. [Paper]

  40. Hierarchical Memory Organization for Wikipedia Generation
    Eugene J. Yu, Dawei Zhu, Yifan Song, et al. ACL 2025. [Paper]

  41. HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model
    Mengkang Hu, Tianxing Chen, Qiguang Chen, et al. ACL 2025. [Paper] [Code]

  42. Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge
    Haomiao Xiong, Zongxin Yang, Jiazuo Yu, et al. ICLR 2025. [Paper]

  43. From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs
    Alireza Rezazadeh, Zichao Li, Wei Wei, Yujia Bao. ICLR 2025. [Paper]

  44. HMT: Hierarchical Memory Transformer for Efficient Long Context Language Processing
    Zifan He, Yingqi Cao, Zongyue Qin, et al. NAACL 2025. [Paper]

  45. Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinement
    Saman Forouzandeh, Wei Peng, Parham Moradi, et al. arXiv 2025. [Paper]

  46. Adapting Like Humans: A Metacognitive Agent with Test-time Reasoning
    Yang Li, Zhiyuan He, Yuxuan Huang, et al. arXiv 2025. [Paper]

  47. O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents
    Piaohong Wang, Motong Tian, Jiaxian Li, et al. arXiv 2025. [Paper]

  48. Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action Memory
    Shiqi He, Yue Cui, Xinyu Ma, et al. arXiv 2025. [Paper]

  49. MoM: Mixtures of Scenario-Aware Document Memories for Retrieval-Augmented Generation Systems
    Jihao Zhao, Zhiyuan Ji, Simin Niu, et al. arXiv 2025. [Paper]

  50. Scaling Long-Horizon LLM Agent via Context-Folding
    Weiwei Sun, Miao Lu, Zhan Ling, et al. arXiv 2025. [Paper]

  51. Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks
    Cheng Yang, Xuemeng Yang, Licheng Wen, et al. arXiv 2025. [Paper]

  52. H²R: Hierarchical Hindsight Reflection for Multi-Task LLM Agents
    Shicheng Ye, Chao Yu, Kaiqiang Ke, et al. arXiv 2025. [Paper]

  53. Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents
    Haoran Sun, Shaoning Zeng. arXiv 2025. [Paper]

  54. G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
    Guibin Zhang, Muxin Fu, Guancheng Wan, et al. arXiv 2025. [Paper] [Code]

  55. Efficiently Enhancing General Agents With Hierarchical-categorical Memory
    Changze Qiao, Mingming Lu. arXiv 2025. [Paper]

  56. From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents
    Derong Xu, Yi Wen, Pengyue Jia, et al. arXiv 2025. [Paper]

  57. RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
    Parth Sarthi, Salman Abdullah, Aditi Tuli, et al. ICLR 2024. [Paper] [Code]

  58. FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design
    Yangyang Yu, Haohang Li, Zhi Chen, et al. AAAI Spring Symposium 2024. [Paper] [Code]

  59. Enhancing Long-Term Memory using Hierarchical Aggregate Tree for Retrieval Augmented Generation
    Aadharsh Aadhithya A, Sachin Kumar S, Soman K. P. arXiv 2024. [Paper]

⬆️ top

1.3 Composite Memory Systems

Systems combining multiple memory representations, stores, modalities, time scales, or operating-system-like management policies.

  1. Closing the Feedback Loop: From Experience Extraction to Insight Governance in Verbal Reinforcement Learning
    Yanwei Cui, Xing Zhang, Yulong Zhang, et al. ICML 2026. [Paper]

  2. Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics
    Andreas Pattichis, Constantine Dovrolis. ICML 2026. [Paper]

  3. E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent Memory
    Kaixiang Wang, Yidan Lin, Jiong Lou, et al. ICML 2026. [Paper]

  4. Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory
    Sijia Li, Yuchen Huang, Zifan Liu, et al. ICML 2026. [Paper]

  5. RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents
    Zijie Dai, Shiyuan Deng, Sheng Guan, et al. ACL 2026. [Paper]

  6. HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents
    Jinchang Zhu, Jindong Li, Cheng Zhang, et al. ACL 2026. [Paper]

  7. MemoPhishAgent: Memory-Augmented Multi-Modal LLM Agent for Phishing URL Detection
    Xuan Chen, Hao Liu, Tao Yuan, et al. ACL 2026. [Paper]

  8. PersonaAgent: Bridging Memory and Action for Personalized LLM Agents
    Weizhi Zhang, Xinyang Zhang, Chenwei Zhang, et al. ACL 2026. [Paper]

  9. PersonaVLM: Long-Term Personalized Multimodal LLMs
    Chang Nie, Chaoyou Fu, Yifan Zhang, et al. CVPR 2026. [Paper]

  10. HippoMM: Hippocampal-inspired Multimodal Memory for Long Audiovisual Event Understanding
    Yueqian Lin, Jingyang Zhang, Qinsi Wang, et al. CVPR 2026. [Paper]

  11. HIMM: Human-Inspired Long-Term Memory Modeling for Embodied Exploration and Question Answering
    Ji Li, Bo Wang, Jing Xia, et al. IROS 2026. [Paper]

  12. Multi-agent In-context Coordination via Decentralized Memory Retrieval
    Tao Jiang, Zichuan Lin, Lihe Li, et al. AAAI 2026. [Paper]

  13. Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces
    Shreyas Rajesh, Pavan Holur, Chenda Duan, et al. AAAI 2026. [Paper]

  14. LightMem: Lightweight and Efficient Memory-Augmented Generation
    Jizhan Fang, Xinle Deng, Haoming Xu, et al. ICLR 2026. [Paper] [Code]

  15. MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding
    Peiran Wu, Zhuorui Yu, Yunze Liu, et al. ICLR 2026. [Paper]

  16. Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory Utilization
    Taeyoon Kwon, Dongwook Choi, Hyojun Kim, et al. ICLR 2026. [Paper]

  17. Mandol: An Agglomerative Agent Memory System for Long-Term Conversations
    Yuhan Zhang, Zhiyuan Guo, Ziheng Zeng, et al. arXiv 2026. [Paper]

  18. AtomMem: Building Simple and Effective Memory System for LLM Agents via Atomic Facts
    Yanyu Yao, Shangze Li, Zhi Zheng, et al. arXiv 2026. [Paper]

  19. FinAcumen: Financial Multimodal Reasoning via Self-Evolving Experience Memory Harness
    Pianran Guo, Pengcheng Zhou, Yucheng Jian, et al. arXiv 2026. [Paper]

  20. User as Code: Executable Memory for Personalized Agents
    Bojie Li. arXiv 2026. [Paper]

  21. ActiveMem: Distributed Active Memory for Long-Horizon LLM Reasoning
    Yunhan Jiang, Wenbin Duan, Shasha Guo, et al. arXiv 2026. [Paper]

  22. Memory Beyond Recall: A Dual-Process Cognitive Memory System for Self-Evolving LLM Agents
    Tianxiang Fei, Mingyang Song, Mao Zheng, et al. arXiv 2026. [Paper]

  23. AdMem: Advanced Memory for Task-solving Agents
    Runzhe Wang, Huilin Lu, Shengjie Liu, et al. arXiv 2026. [Paper]

  24. AdaMEM: Test-Time Adaptive Memory for Language Agents
    Yunxiang Zhang, Yiheng Li, Ali Payani, et al. arXiv 2026. [Paper]

  25. SaliMory: Orchestrating Cognitive Memory for Conversational Agents
    Kai Zhang, Xinyuan Zhang, Hongda Jiang, et al. arXiv 2026. [Paper]

  26. eMEM: A Hybrid Spatio-Temporal Memory System For Embodied Agents
    A. Haroon Rasheed, Maria Kabtoul. arXiv 2026. [Paper]

  27. CoMIC: Collaborative Memory and Insights Circulation for Long-Horizon LLM Agents in Cloud-Edge Systems
    Yannan Wang, Longli Yang, Zhen Liu, et al. arXiv 2026. [Paper]

  28. Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents
    Ziyan Liu, Zhezheng Hao, Yeqiu Chen, et al. arXiv 2026. [Paper]

  29. Self-Evolving Multi-Agent Systems via Decentralized Memory
    Guangya Hao, Yunbo Long, Zhuokai Zhao. arXiv 2026. [Paper]

  30. MemCompiler: Compile, Don't Inject -- State-Conditioned Memory for Embodied Agents
    Xin Ding, Xinrui Wang, Yifan Yang, et al. arXiv 2026. [Paper]

  31. Governed Collaborative Memory as Artificial Selection in LLM-Based Multi-Agent Systems
    Diego F. Cuadros, Abdoul-Aziz Maiga, Helen Meskhidze, et al. arXiv 2026. [Paper]

  32. ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting
    Jiale Chang, Yuxiang Ren. arXiv 2026. [Paper]

  33. Detecting Clinical Discrepancies in Health Coaching Agents: A Dual-Stream Memory and Reconciliation Architecture
    Samuel L Pugh, Eric Yang, Alexander Muir Sutherland, et al. arXiv 2026. [Paper]

  34. Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents
    Yuxuan Cai, Wei Li, Jie Zhou, et al. arXiv 2026. [Paper]

  35. M★: Every Task Deserves Its Own Memory Harness
    Wenbo Pan, Shujie Liu, Xiangyang Zhou, et al. arXiv 2026. [Paper]

  36. ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM Agents
    Mofasshara Rafique, Laurent Bindschaedler. arXiv 2026. [Paper]

  37. MEMENTO: Teaching LLMs to Manage Their Own Context
    Vasilis Kontonis, Yuchen Zeng, Shivam Garg, et al. arXiv 2026. [Paper]

  38. Towards Lifelong Aerial Autonomy: Geometric Memory Management for Continual Visual Place Recognition in Dynamic Environments
    Xingyu Shao, Zhiqiang Yan, Liangzheng Sun, et al. arXiv 2026. [Paper]

  39. StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding
    Junxi Wang, Te Sun, Jiayi Zhu, et al. arXiv 2026. [Paper]

  40. MemCoT: Test-Time Scaling through Memory-Driven Chain-of-Thought
    Haodong Lei, Junming Liu, Yirong Chen, et al. arXiv 2026. [Paper]

  41. PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory
    Zhifei Xie, Zongzheng Hu, Fangda Ye, et al. arXiv 2026. [Paper]

  42. FileGram: Grounding Agent Personalization in File-System Behavioral Traces
    Shuai Liu, Shulin Tian, Kairui Hu, et al. arXiv 2026. [Paper]

  43. Memory Intelligence Agent
    Jingyang Qiao, Weicheng Meng, Yu Cheng, et al. arXiv 2026. [Paper]

  44. Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems
    Shanglin Wu, Yuyang Luo, Yueqing Liang, et al. arXiv 2026. [Paper]

  45. Aligning Progress and Feasibility: A Neuro-Symbolic Dual Memory Framework for Long-Horizon LLM Agents
    Bin Wen, Ruoxuan Zhang, Yang Chen, et al. arXiv 2026. [Paper]

  46. Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory
    Jiaqi Liu, Zipeng Ling, Shi Qiu, et al. arXiv 2026. [Paper]

  47. MemFactory: Unified Inference & Training Framework for Agent Memory
    Ziliang Guo, Ziheng Li, Bo Tang, et al. arXiv 2026. [Paper]

  48. Multi-Layered Memory Architectures for LLM Agents: An Experimental Evaluation of Long-Term Context Retention
    Sunil Tiwari, Payal Fofadiya. arXiv 2026. [Paper]

  49. MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution
    Minhua Lin, Zhiwei Zhang, Hanqing Lu, et al. arXiv 2026. [Paper]

  50. ReMem-VLA: Empowering Vision-Language-Action Model with Memory via Dual-Level Recurrent Queries
    Hang Li, Fengyi Shen, Dong Chen, et al. arXiv 2026. [Paper]

  51. Joint Optimization of Multi-agent Memory System
    Wenyu Mao, Haoyang Liu, Haosong Tan, et al. arXiv 2026. [Paper]

  52. Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models
    Lu Wang, Zhuoran Jin, Yupu Hao, et al. arXiv 2026. [Paper]

  53. MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games
    Yunfei Xie, Kevin Wang, Bobby Cheng, et al. arXiv 2026. [Paper]

  54. MMA: Multimodal Memory Agent
    Yihao Lu, Wanru Cheng, Zeyu Zhang, et al. arXiv 2026. [Paper]

  55. Choosing How to Remember: Adaptive Memory Structures for LLM Agents
    Mingfei Lu, Mengjia Wu, Feng Liu, et al. arXiv 2026. [Paper]

  56. HyMem: Hybrid Memory Architecture with Dynamic Retrieval Scheduling
    Xiaochen Zhao, Kaikai Wang, Xiaowen Zhang, et al. arXiv 2026. [Paper]

  57. STaR: Scalable Task-Conditioned Retrieval for Long-Horizon Multimodal Robot Memory
    Mingfeng Yuan, Hao Zhang, Mahan Mohammadi, et al. arXiv 2026. [Paper]

  58. M2A: Multimodal Memory Agent with Dual-Layer Hybrid Memory for Long-Term Personalized Interactions
    Junyu Feng, Binxiao Xu, Jiayi Chen, et al. arXiv 2026. [Paper]

  59. MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning
    Yaorui Shi, Shugui Liu, Yu Yang, et al. arXiv 2026. [Paper]

  60. MemCtrl: Using MLLMs as Active Memory Controllers on Embodied Agents
    Vishnu Sashank Dorbala, Dinesh Manocha. arXiv 2026. [Paper]

  61. BMAM: Brain-inspired Multi-Agent Memory Framework
    Yang Li, Jiaxiang Liu, Yusong Wang, et al. arXiv 2026. [Paper]

  62. AMA: Adaptive Memory via Multi-Agent Collaboration
    Weiquan Huang, Zixuan Wang, Hehai Lin, et al. arXiv 2026. [Paper]

  63. MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic Reasoning
    Juexiang Ye, Xue Li, Xinyu Yang, et al. arXiv 2026. [Paper]

  64. Continuum Memory Architectures for Long-Horizon LLM Agents
    Joe Logan. arXiv 2026. [Paper]

  65. Structured Episodic Event Memory
    Zhengxuan Lu, Dongfang Li, Yukun Shi, et al. arXiv 2026. [Paper]

  66. HiMeS: Hippocampus-inspired Memory System for Personalized AI Assistants
    Hailong Li, Feifei Li, Wenhui Que, et al. arXiv 2026. [Paper]

  67. EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning
    Chuanrui Hu, Xingze Gao, Zuyi Zhou, et al. arXiv 2026. [Paper]

  68. Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents
    Yi Yu, Liuyi Yao, Yuexiang Xie, et al. arXiv 2026. [Paper]

  69. FluctlightDB: A Memory Model of Data for AI Agents
    Ganesh S. Zenodo 2026. [Paper] [Github]

  70. VideoLucy: Deep Memory Backtracking for Long Video Understanding
    Jialong Zuo, Yongtai Deng, Lingdong Kong, et al. NeurIPS 2025. [Paper]

  71. Memory OS of AI Agent
    Jiazheng Kang, Mingming Ji, Zhe Zhao, Ting Bai. EMNLP 2025. [Paper] [Code]

  72. M2PA: A Multi-Memory Planning Agent for Open Worlds Inspired by Cognitive Theory
    Yanfang Zhou, Xiaodong Li, Yuntao Liu, et al. Findings of ACL 2025. [Paper]

  73. Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
    Prateek Chhikara, Dev Khant, Saket Aryan, et al. ECAI 2025. [Paper] [Code]

  74. TReMu: Towards Neuro-Symbolic Temporal Reasoning for LLM-Agents with Memory in Multi-Session Dialogues
    Yubin Ge, Salvatore Romeo, Jason Cai, et al. ACL 2025. [Paper]

  75. JARVIS-1: Open-World Multi-Task Agents with Memory-Augmented Multimodal Language Models
    Zihao Wang, Shaofei Cai, Anji Liu, et al. IEEE TPAMI 2025. [Paper] [Code]

  76. TeleMem: Building Long-Term and Multimodal Memory for Agentic AI
    Chunliang Chen, Ming Guan, Xiao Lin, et al. arXiv 2025. [Paper]

  77. Context as a Tool: Context Management for Long-Horizon SWE-Agents
    Shukai Liu, Jian Yang, Bo Jiang, et al. arXiv 2025. [Paper]

  78. Memory Bear AI A Breakthrough from Memory to Cognition Toward Artificial General Intelligence
    Deliang Wen, Ke Sun. arXiv 2025. [Paper]

  79. MemEvolve: Meta-Evolution of Agent Memory Systems
    Guibin Zhang, Haotian Ren, Chong Zhan, et al. arXiv 2025. [Paper]

  80. Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects
    Chris Latimer, Nicoló Boschi, Andrew Neeser, et al. arXiv 2025. [Paper]

  81. Memoria: A Scalable Agentic Memory Framework for Personalized Conversational AI
    Samarth Sarin, Lovepreet Singh, Bhaskarjit Sarmah, et al. arXiv 2025. [Paper]

  82. Unifying Dynamic Tool Creation and Cross-Task Experience Sharing through Cognitive Memory Architecture
    Jiarun Liu, Shiyue Xu, Yang Li, et al. arXiv 2025. [Paper]

  83. MemVerse: Multimodal Memory for Lifelong Learning Agents
    Junming Liu, Yifei Sun, Weihua Cheng, et al. arXiv 2025. [Paper]

  84. Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration
    Zhongyi Cai, Yi Du, Chen Wang, et al. arXiv 2025. [Paper]

  85. WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning
    Woongyeong Yeo, Kangsan Kim, Jaehong Yoon, et al. arXiv 2025. [Paper]

  86. MMAG: Mixed Memory-Augmented Generation for Large Language Models Applications
    Stefano Zeppieri. arXiv 2025. [Paper]

  87. MG-Nav: Dual-Scale Visual Navigation via Sparse Spatial Memory
    Bo Wang, Jiehong Lin, Chenzhi Liu, et al. arXiv 2025. [Paper]

  88. Agentic Learner with Grow-and-Refine Multimodal Semantic Memory
    Weihao Bo, Shan Zhang, Yanpeng Sun, et al. arXiv 2025. [Paper]

  89. General Agentic Memory Via Deep Research
    B. Y. Yan, Chaofan Li, Hongjin Qian, et al. arXiv 2025. [Paper]

  90. MirrorMind: Empowering OmniScientist with the Expert Perspectives and Collective Knowledge of Human Scientists
    Qingbin Zeng, Bingbing Fan, Zhiyu Chen, et al. arXiv 2025. [Paper]

  91. ENGRAM: Effective, Lightweight Memory Orchestration for Conversational Agents
    Daivik Patel, Shrenik Patel. arXiv 2025. [Paper]

  92. GCAgent: Long-Video Understanding via Schematic and Narrative Episodic Memory
    Jeong Hun Yeo, Sangyun Chung, Sungjune Park, et al. arXiv 2025. [Paper]

  93. EvoMem: Improving Multi-Agent Planning with Dual-Evolving Memory
    Wenzhe Fan, Ning Yan, Masood Mortazavi. arXiv 2025. [Paper]

  94. CRMWeaver: Building Powerful Business Agent via Agentic RL and Shared Memories
    Yilong Lai, Yipin Yang, Jialong Wu, et al. arXiv 2025. [Paper]

  95. MGA: Memory-Driven GUI Agent for Observation-Centric Interaction
    Weihua Cheng, Junming Liu, Yifei Sun, et al. arXiv 2025. [Paper]

  96. PISA: A Pragmatic Psych-Inspired Unified Memory System for Enhanced AI Agency
    Shian Jia, Ziyang Huang, Xinbo Wang, et al. arXiv 2025. [Paper]

  97. D-SMART: Enhancing LLM Dialogue Consistency via Dynamic Structured Memory And Reasoning Tree
    Xiang Lei, Qin Li, Min Zhang, et al. arXiv 2025. [Paper]

  98. ToolMem: Enhancing Multimodal Agents with Learnable Tool Capability Memory
    Yunzhong Xiao, Yangmin Li, Hewei Wang, et al. arXiv 2025. [Paper]

  99. LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation
    Dongge Han, Camille Couturier, Daniel Madrigal Diaz, et al. arXiv 2025. [Paper]

  100. Mem-α: Learning Memory Construction via Reinforcement Learning
    Yu Wang, Ryuichi Takanobu, Zhiqi Liang, et al. arXiv 2025. [Paper]

  101. Memory Management and Contextual Consistency for Long-Running Low-Code Agents
    Jiexi Xu. arXiv 2025. [Paper]

  102. MOOM: Maintenance, Organization and Optimization of Memory in Ultra-Long Role-Playing Dialogues
    Weishu Chen, Jinyi Tang, Zhouhui Hou, et al. arXiv 2025. [Paper]

  103. Text2Mem: A Unified Memory Operation Language for Memory Operating System
    Yi Wang, Lihai Yang, Boyu Chen, et al. arXiv 2025. [Paper]

  104. SEDM: Scalable Self-Evolving Distributed Memory for Agents
    Haoran Xu, Jiacong Hu, Ke Zhang, et al. arXiv 2025. [Paper]

  105. Livia: An Emotion-Aware AR Companion Powered by Modular AI Agents and Progressive Memory Compression
    Rui Xi, Xianghan Wang. arXiv 2025. [Paper]

  106. Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
    Lin Long, Yichen He, Wentao Ye, et al. arXiv 2025. [Paper]

  107. Video-EM: Event-Centric Episodic Memory for Long-Form Video Understanding
    Yun Wang, Long Zhang, Jingren Liu, et al. arXiv 2025. [Paper]

  108. Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory
    Sizhe Yuen, Francisco Gomez Medina, Ting Su, et al. arXiv 2025. [Paper]

  109. RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory
    Jun Liu, Zhenglun Kong, Changdi Yang, et al. arXiv 2025. [Paper]

  110. What Deserves Memory: Adaptive Memory Distillation for LLM Agents
    Wenquan Ma, Jiayan Nan, Wenlong Wu, et al. arXiv 2025. [Paper]

  111. MIRIX: Multi-Agent Memory System for LLM-Based Agents
    Yu Wang, Xi Chen. arXiv 2025. [Paper] [Code]

  112. PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Process
    Xinliang Frederick Zhang, Nick Beauchamp, Lu Wang. arXiv 2025. [Paper]

  113. MemOS: A Memory OS for AI System
    Zhiyu Li, Chenyang Xi, Chunyu Li, et al. arXiv 2025. [Paper] [Code]

  114. Ella: Embodied Social Agents with Lifelong Memory
    Hongxin Zhang, Zheyuan Zhang, Zeyuan Wang, et al. arXiv 2025. [Paper]

  115. Xolver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Team
    Md Tanzib Hosain, Salman Rahman, Md Kishor Morol, et al. arXiv 2025. [Paper]

  116. MAPLE: Multi-Agent Adaptive Planning with Long-Term Memory for Table Reasoning
    Ye Bai, Minghan Wang, Thuy-Trang Vu. arXiv 2025. [Paper]

  117. 3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model
    Wenbo Hu, Yining Hong, Yanjun Wang, et al. arXiv 2025. [Paper]

  118. Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control
    Alireza Rezazadeh, Zichao Li, Ange Lou, et al. arXiv 2025. [Paper]

  119. Pre-training Limited Memory Language Models with Internal and External Knowledge
    Linxi Zhao, Sofian Zalouk, Christian K. Belardi, et al. arXiv 2025. [Paper]

  120. AI-native Memory 2.0: Second Me
    Jiale Wei, Xiang Ying, Tao Gao, et al. arXiv 2025. [Paper]

  121. Enhancing Reasoning with Collaboration and Memory
    Julie Michelman, Nasrin Baratalipour, Matthew Abueg. arXiv 2025. [Paper]

  122. Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation
    Lingfeng Zhang, Yuecheng Liu, Zhanguang Zhang, et al. arXiv 2025. [Paper]

  123. SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation
    Haoquan Fang, Markus Grotz, Wilbert Pumacay, et al. arXiv 2025. [Paper]

  124. SRMT: Shared Memory for Multi-agent Lifelong Pathfinding
    Alsu Sagirova, Yuri Kuratov, Mikhail Burtsev. arXiv 2025. [Paper]

  125. Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks
    Zaijing Li, Yuquan Xie, Rui Shao, et al. NeurIPS 2024. [Paper] [Code]

  126. VideoAgent: A Memory-Augmented Multimodal Agent for Video Understanding
    Yue Fan, Xiaojian Ma, Rujie Wu, et al. ECCV 2024. [Paper] [Code]

  127. Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding
    Yue Fan, Xiaojian Ma, Rongpeng Su, et al. arXiv 2024. [Paper]

  128. A Machine with Short-Term, Episodic, and Semantic Memory Systems
    Taewoon Kim, Michael Cochez, Vincent François-Lavet, et al. AAAI 2023. [Paper]

  129. MemGPT: Towards LLMs as Operating Systems
    Charles Packer, Sarah Wooders, Kevin Lin, et al. arXiv 2023. [Paper] [Code]

⬆️ top

1.4 Baselines and Supporting Methods

Foundational retrieval, reasoning, reflection, and context-management methods commonly used as baselines or components in agent-memory studies.

  1. Visual Inception: Compromising Long-term Planning in Agentic Recommenders via Multimodal Memory Poisoning
    Jiachen Qian. ACL 2026. [Paper]

  2. Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections
    Xianglin Yang, Yufei He, Shuo Ji, et al. ICLR 2026. [Paper]

  3. What Must Generalist Agents Remember?
    Khurram Yamin, Namrata Deka, Maitreyi Swaroop, et al. arXiv 2026. [Paper]

  4. Control-Plane Placement Shapes Forgetting: An Architectural Study of Agent Memory Across Thirteen System Configurations
    Dongxu Yang. arXiv 2026. [Paper]

  5. FragFuse: Bypassing Access Control of Large Language Model Agents via Memory-Based Query Fragmentation and Fusion
    Zixin Rao, Wentian Zhu, Chan Aristella Lu, et al. arXiv 2026. [Paper]

  6. Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads
    Yasmine Omri, Ziyu Gan, Zachary Broveak, et al. arXiv 2026. [Paper]

  7. Beyond Similarity: Trustworthy Memory Search for Personal AI Agents
    Jiawen Zhang, Kejia Chen, Jiachen Ma, et al. arXiv 2026. [Paper]

  8. Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense
    Minseok Choi, Seungbin Yang, Dongjin Kim, et al. arXiv 2026. [Paper]

  9. From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
    Pritam Dash, Tongyu Ge, Aditi Jain, et al. arXiv 2026. [Paper]

  10. Don't Ask the LLM to Track Freshness: A Deterministic Recipe for Memory Conflict Resolution
    Vikas Reddy, Sumanth Challaram. arXiv 2026. [Paper]

  11. MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents
    Yining Chen, Jihao Zhao, Bo Tang, et al. arXiv 2026. [Paper]

  12. Storage Is Not Memory: A Retrieval-Centered Architecture for Agent Recall
    Joshua Adler, Guy Zehavi. arXiv 2026. [Paper]

  13. MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents
    Ishrith Gowda. arXiv 2026. [Paper]

  14. What Happens Inside Agent Memory? Circuit Analysis from Emergence to Diagnosis
    Xutao Mao, Jinman Zhao, Gerald Penn, et al. arXiv 2026. [Paper]

  15. MAGE: Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory
    Yuhui Wang, Tanqiu Jiang, Jiacheng Liang, et al. arXiv 2026. [Paper]

  16. ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying
    Xingyu Lyu, Jianfeng He, Ning Wang, et al. arXiv 2026. [Paper]

  17. Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents
    Wei Zou, Mingwen Dong, Miguel Romero Calvo, et al. arXiv 2026. [Paper]

  18. Emerging Human-like Strategies for Semantic Memory Foraging in Large Language Models
    Eric Lacosse, Mariana Duarte, Peter M. Todd, et al. arXiv 2026. [Paper]

  19. ER-MIA: Black-Box Adversarial Memory Injection Attacks on Long-Term Memory-Augmented Large Language Models
    Mitchell Piehl, Zhaohan Xi, Zuobin Xiong, et al. arXiv 2026. [Paper]

  20. MemPot: Defending Against Memory Extraction Attack with Optimized Honeypots
    Yuhao Wang, Shengfang Zhai, Guanghao Jin, et al. arXiv 2026. [Paper]

  21. Memory Retrieval in Transformers: Insights from The Encoding Specificity Principle
    Viet Hung Dinh, Ming Ding, Youyang Qu, et al. arXiv 2026. [Paper]

  22. GLOVE: Global Verifier for LLM Memory-Environment Realignment
    Xingkun Yin, Hongyang Du. arXiv 2026. [Paper]

  23. Disentangling Memory and Reasoning Ability in Large Language Models
    Mingyu Jin, Weidi Luo, Sitao Cheng, et al. ACL 2025. [Paper]

  24. Beyond Heuristics: A Decision-Theoretic Framework for Agent Memory Management
    Changzhi Sun, Xiangyu Chen, Jixiang Luo, et al. arXiv 2025. [Paper]

  25. Can an LLM Induce a Graph? Investigating Memory Drift and Context Length
    Raquib Bin Yousuf, Aadyant Khatri, Shengzhe Xu, et al. arXiv 2025. [Paper]

  26. Cognitive Workspace: Active Memory Management for LLMs -- An Empirical Study of Functional Infinite Context
    Tao An. arXiv 2025. [Paper]

  27. How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
    Zidi Xiong, Yuping Lin, Wenya Xie, et al. arXiv 2025. [Paper]

  28. Unveiling Privacy Risks in LLM Agent Memory
    Bo Wang, Weiyi He, Shenglai Zeng, et al. arXiv 2025. [Paper]

  29. Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
    Ling Yang, Zhaochen Yu, Tianjun Zhang, et al. NeurIPS 2024 Spotlight. [Paper] [Code]

  30. Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
    Akari Asai, Zeqiu Wu, Yizhong Wang, et al. ICLR 2024. [Paper] [Code]

  31. From Local to Global: A Graph RAG Approach to Query-Focused Summarization
    Darren Edge, Ha Trinh, Newman Cheng, et al. arXiv 2024. [Paper] [Code]

  32. Reflexion: Language Agents with Verbal Reinforcement Learning
    Noah Shinn, Federico Cassano, Edward Berman, et al. NeurIPS 2023. [Paper] [Code]

  33. ReAct: Synergizing Reasoning and Acting in Language Models
    Shunyu Yao, Jeffrey Zhao, Dian Yu, et al. ICLR 2023. [Paper] [Code]

  34. Unsupervised Dense Information Retrieval with Contrastive Learning
    Gautier Izacard, Mathilde Caron, Lucas Hosseini, et al. TMLR 2022. [Paper] [Code]

  35. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
    Patrick Lewis, Ethan Perez, Aleksandra Piktus, et al. NeurIPS 2020. [Paper]

  36. The Probabilistic Relevance Framework: BM25 and Beyond
    Stephen Robertson, Hugo Zaragoza. Foundations and Trends in Information Retrieval 2009. [Paper]

⬆️ top

2. Benchmarks and Datasets

Each benchmark appears once under its primary evaluation purpose; third-line tags record secondary dimensions.

2.1 Effectiveness Evaluation

Benchmarks centered on answer quality, task success, action correctness, or end-to-end agent capability.

  1. EmbodiedMemory-Bench: Benchmarking Embodied Memory for Long-Horizon Embodied Tasks
    Lizhou Liang, Xinyu Zhong, Miao Pan, et al. arXiv 2026. [Paper] [Code]

  2. StratMem-Bench: Evaluating Strategic Memory Use in Virtual Character Conversation Beyond Factual Recall
    Yerong Wu, Tianxing Wu, Minghao Zhu, et al. ACL 2026. [Paper]

  3. AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations
    Cheng Jiayang, Dongyu Ru, Lin Qiu, et al. ICLR 2026. [Paper]

  4. Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline
    Zhikai Chen, Jialiang Gu, Junyu Yin, et al. arXiv 2026. [Paper]

  5. Momento: Evaluating Persistent Memory and Reasoning with Multi-Session Agentic Conversations
    Adril Putra Merin, David Anugraha, Ayu Purwarianti, et al. arXiv 2026. [Paper]

  6. WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction
    Chengzhi Liu, Yuzhe Yang, Sophia Xiao Pu, et al. arXiv 2026. [Paper]

  7. RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark
    Huashuo Lei, Wenxuan Song, Huarui Zhang, et al. arXiv 2026. [Paper]

  8. MemEmo: Evaluating Emotion in Memory Systems of Agents
    Peng Liu, Zhen Tao, Jihao Zhao, et al. arXiv 2026. [Paper]

  9. AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications
    Yujie Zhao, Boqin Yuan, Junbo Huang, et al. arXiv 2026. [Paper]

  10. MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks
    Zexue He, Yu Wang, Churan Zhi, et al. arXiv 2026. [Paper]

  11. Mem2ActBench: A Benchmark for Evaluating Long-Term Memory Utilization in Task-Oriented Autonomous Agents
    Yiting Shen, Kun Li, Wei Zhou, et al. arXiv 2026. [Paper]

  12. How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistants
    Xueyang Feng, Weinan Gan, Xu Chen, et al. arXiv 2026. [Paper]

  13. MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models
    Zecheng Tang, Baibei Ji, Ruoxi Sun, et al. arXiv 2026. [Paper]

  14. RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction
    Haonan Bian, Zhiyuan Yao, Sen Hu, et al. arXiv 2026. [Paper]

  15. KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions
    Tingyu Wu, Zhisheng Chen, Ziyan Weng, et al. arXiv 2026. [Paper]

  16. LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks
    Yushi Bai, Shangqing Tu, Jiajie Zhang, et al. ACL 2025. [Paper] [Code] [Dataset]

  17. Explicit v.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized Information
    Zeyu Zhang, Yang Zhang, Haoran Tan, et al. arXiv 2025. [Paper]

  18. StoryBench: A Dynamic Benchmark for Evaluating Long-Term Memory with Multi Turns
    Luanbo Wan, Weizhi Ma. arXiv 2025. [Paper]

  19. Episodic Memories Generation and Evaluation Benchmark for Large Language Models
    Alexis Huet, Zied Ben Houidi, Dario Rossi. arXiv 2025. [Paper]

  20. OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
    Tianbao Xie, Danyang Zhang, Jixuan Chen, et al. NeurIPS 2024 Datasets and Benchmarks. [Paper] [Code] [Dataset]

  21. AgentBench: Evaluating LLMs as Agents
    Xiao Liu, Hao Yu, Hanchen Zhang, et al. ICLR 2024. [Paper] [Code] [Dataset]

  22. WebArena: A Realistic Web Environment for Building Autonomous Agents
    Shuyan Zhou, Frank F. Xu, Hao Zhu, et al. ICLR 2024. [Paper] [Code] [Dataset]

  23. MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants
    Zeyu Zhang, Quanyu Dai, Luyu Chen, et al. arXiv 2024. [Paper] [Code] [Dataset]

⬆️ top

2.2 Retrieval Evaluation

Benchmarks focused on recalling facts, evidence, events, or relevant context over long documents and multi-session interactions.

  1. MemTrace: Probing What Final Accuracy Misses in Long-Term Memory
    Xianxuan Long, Zhikai Chen, Shenglai Zeng, et al. arXiv 2026. [Paper]

  2. StreamMemBench: Streaming Evaluation of Agent Memory for Future-Oriented Assistance
    Guanming Liu, Yuqi Ren, Hansu Gu, et al. arXiv 2026. [Paper]

  3. Substrate Asymmetry in User-Side Memory: A Diagnostic Framework
    Youwang Deng. arXiv 2026. [Paper]

  4. H2HMem: A Multimodal Memory Benchmark for Agents in Human-Human Interactions
    Shiping Zhu, Yibo Yang, Zhengyang Wang, et al. arXiv 2026. [Paper]

  5. SubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents
    Wenxuan Wang, Haoyu Sun, Fukuan Hou, et al. arXiv 2026. [Paper]

  6. MemoryDocDataSet: A Benchmark for Joint Conversational Memory and Long Document Reasoning
    Qiyang Xie, Jialun Wu, Xinjie He, et al. arXiv 2026. [Paper]

  7. Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue
    Jingjie Lin, Bingbing Wang, Zihan Wang, et al. arXiv 2026. [Paper]

  8. SuperMemory-VQA: An Egocentric Visual Question-Answering Benchmark for Long-Horizon Memory
    Samiul Alam, Shakhrul Iman Siam, Michael J. Proulx, et al. arXiv 2026. [Paper]

  9. EGOSTREAM: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision
    Rosario Forte, Giuseppe Lando, Antonino Furnari. arXiv 2026. [Paper]

  10. Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory
    Han Zhang, Zihao Tang, Xin Yu, et al. arXiv 2026. [Paper]

  11. MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory
    Minghao Guo, Qingyue Jiao, Zeru Shi, et al. arXiv 2026. [Paper]

  12. Structured Belief State and the First Precision-Aware Benchmark for LLM Memory Retrieval
    Jeffrey Flynt. arXiv 2026. [Paper]

  13. LifeBench: A Benchmark for Long-Horizon Multi-Source Memory
    Zihao Cheng, Weixin Wang, Yu Zhao, et al. arXiv 2026. [Paper]

  14. Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents
    Yifei Li, Weidong Guo, Lingling Zhang, et al. arXiv 2026. [Paper]

  15. CloneMem: Benchmarking Long-Term Memory for AI Clones
    Sen Hu, Zhiyu Zhang, Yuxiang Wei, et al. arXiv 2026. [Paper]

  16. EvolMem: A Cognitive-Driven Benchmark for Multi-Session Dialogue Memory
    Ye Shen, Dun Pei, Yiqiu Guo, et al. arXiv 2026. [Paper]

  17. Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents
    Yuanchen Bei, Tianxin Wei, Xuying Ning, et al. arXiv 2026. [Paper]

  18. Evaluating the Long-Term Memory of Large Language Models
    Zixi Jia, Qinghua Liu, Hexiao Li, et al. Findings of ACL 2025. [Paper]

  19. Toward Multi-Session Personalized Conversation: A Large-Scale Dataset and Hierarchical Tree Framework for Implicit Reasoning
    Xintong Li, Jalend Bantupalli, Ria Dharmani, et al. EMNLP 2025. [Paper]

  20. Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs
    Siyan Zhao, Mingyi Hong, Yang Liu, et al. ICLR 2025. [Paper]

  21. LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
    Di Wu, Hongwei Wang, Wenhao Yu, et al. ICLR 2025. [Paper] [Code] [Dataset]

  22. MADial-Bench: Towards Real-world Evaluation of Memory-Augmented Dialogue Generation
    Junqing He, Liang Zhu, Rui Wang, et al. NAACL 2025. [Paper] [Code] [Dataset]

  23. PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory
    Bowen Jiang, Yuan Yuan, Maohao Shen, et al. arXiv 2025. [Paper]

  24. A Benchmark for Procedural Memory Retrieval in Language Agents
    Ishant Kohar, Aswanth Krishnan. arXiv 2025. [Paper]

  25. Convomem Benchmark: Why Your First 150 Conversations Don't Need RAG
    Egor Pakhomov, Erik Nijkamp, Caiming Xiong. arXiv 2025. [Paper]

  26. TeleEgo: Benchmarking Egocentric AI Assistants in the Wild
    Jiaqi Yan, Ruilong Ren, Jingren Liu, et al. arXiv 2025. [Paper]

  27. Evaluating Long-Term Memory for Long-Context Question Answering
    Alessandra Terranova, Björn Ross, Alexandra Birch. arXiv 2025. [Paper]

  28. Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale
    Bowen Jiang, Zhuoqun Hao, Young-Min Cho, et al. arXiv 2025. [Paper]

  29. REALTALK: A 21-Day Real-World Dataset for Long-Term Conversation
    Dong-Ho Lee, Adyasha Maharana, Jay Pujara, et al. arXiv 2025. [Paper]

  30. Minerva: A Programmable Memory Test Benchmark for Language Models
    Menglin Xia, Victor Ruehle, Saravan Rajmohan, et al. arXiv 2025. [Paper]

  31. RULER: What's the Real Context Size of Your Long-Context Language Models?
    Cheng-Ping Hsieh, Simeng Sun, Samuel Kriman, et al. COLM 2024. [Paper] [Code] [Dataset]

  32. Evaluating Very Long-Term Conversational Memory of LLM Agents
    Adyasha Maharana, Dong-Ho Lee, Sergey Tulyakov, et al. ACL 2024. [Paper] [Code] [Dataset]

  33. ∞Bench: Extending Long Context Evaluation Beyond 100K Tokens
    Xinrong Zhang, Yingfa Chen, Shengding Hu, et al. ACL 2024. [Paper] [Code] [Dataset]

  34. LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
    Yushi Bai, Xin Lv, Jiajie Zhang, et al. ACL 2024. [Paper] [Code] [Dataset]

  35. Beyond Goldfish Memory: Long-Term Open-Domain Conversation
    Jing Xu, Arthur Szlam, Jason Weston. ACL 2022. [Paper] [Dataset]

  36. HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
    Zhilin Yang, Peng Qi, Saizheng Zhang, et al. EMNLP 2018. [Paper] [Code] [Dataset]

⬆️ top

2.3 Robustness Evaluation

Benchmarks stressing continuous learning, conflict resolution, knowledge updates, selective forgetting, or hallucination propagation.

  1. Honest Lying: Understanding Memory Confabulation in Reflexive Agents
    Prakhar Dixit, Sadia Kamal, Tim Oates. ICML 2026. [Paper]

  2. Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs
    Jinbo Liu, Defu Cao, Yifei Wei, et al. ACL 2026. [Paper]

  3. Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
    Yuanzhe Hu, Yu Wang, Julian McAuley. ICLR 2026. [Paper] [Code] [Dataset]

  4. GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents
    Zhe Ren, Yibo Yang, Yimeng Chen, et al. arXiv 2026. [Paper]

  5. EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
    Jundong Xu, Qingchuan Li, Jiaying Wu, et al. arXiv 2026. [Paper]

  6. Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models
    Shelly Bensal, Axel Magnuson, Aparna Balagopalan, et al. arXiv 2026. [Paper]

  7. When Should Memory Stay Silent: Measuring Memory-Use Boundaries in Memory-Augmented Conversational Agents
    Lingxiang Xu, Jiaoyun Yang, Min Hu, et al. arXiv 2026. [Paper]

  8. STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
    Hanxiang Chao, Yihan Bai, Rui Sheng, et al. arXiv 2026. [Paper]

  9. PersistBench: When Should Long-Term Memories Be Forgotten by LLMs?
    Sidharth Pulipaka, Oliver Chen, Manas Sharma, et al. arXiv 2026. [Paper]

  10. MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environments
    Darshan Deshpande, Varun Gangal, Hersh Mehta, et al. NeurIPS 2025. [Paper]

  11. Forgetful but Faithful: A Cognitive Memory Architecture and Benchmark for Privacy-Aware Generative Agents
    Saad Alqithami. arXiv 2025. [Paper]

  12. Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
    Tianxin Wei, Noveen Sachdeva, Benjamin Coleman, et al. arXiv 2025. [Paper]

  13. HaluMem: Evaluating Hallucinations in Memory Systems of Agents
    Ding Chen, Simin Niu, Kehang Li, et al. arXiv 2025. [Paper] [Code] [Dataset]

  14. MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems
    Qingyao Ai, Yichen Tang, Changyue Wang, et al. arXiv 2025. [Paper]

  15. LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners
    Junhao Zheng, Xidi Cai, Qiuke Li, et al. arXiv 2025. [Paper] [Code] [Dataset]

  16. StreamBench: Towards Benchmarking Continuous Improvement of Language Agents
    Cheng-Kuang Wu, Zhi Rui Tam, Chieh-Yen Lin, et al. NeurIPS 2024 Datasets and Benchmarks. [Paper] [Code] [Dataset]

⬆️ top

2.4 Efficiency Evaluation

Benchmarks and studies exposing latency, token use, context scaling, construction cost, maintenance overhead, or task-cost trade-offs.

  1. Are We Ready For An Agent-Native Memory System?
    Wei Zhou, Xuanhe Zhou, Shaokun Han, et al. arXiv 2026. [Paper] [Code] [Dataset]

  2. MEMAUDIT: An Exact Package-Oracle Evaluation Protocol for Budgeted Long-Term LLM Memory Writing
    Nishant Bhargava, Rodrigo Sobral Barrento. arXiv 2026. [Paper]

  3. Beyond the Context Window: A Cost-Performance Analysis of Fact-Based Memory vs. Long-Context LLMs for Persistent Agents
    Natchanon Pollertlam, Witchayut Kornsuwannawit. arXiv 2026. [Paper]

  4. Neuromem: A Granular Decomposition of the Streaming Lifecycle in External Memory for LLMs
    Ruicheng Zhang, Xinyi Li, Tianyi Xu, et al. arXiv 2026. [Paper]

  5. MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments
    Guangyi Liu, Pengxiang Zhao, Yaozhen Liang, et al. arXiv 2026. [Paper] [Code] [Dataset]

  6. Cost and Accuracy of Long-Term Memory in Distributed Multi-Agent Systems Based on Large Language Models
    Benedict Wolff, Jacopo Bennati. arXiv 2026. [Paper]

  7. MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents
    Haoran Tan, Zeyu Zhang, Chen Ma, et al. ACL 2025 Findings. [Paper] [Code] [Dataset]

  8. Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMs
    Mohammad Tavakoli, Alireza Salemi, Carrie Ye, et al. arXiv 2025. [Paper]

⬆️ top

3. Surveys, Tutorials, and Position Papers

  1. Position: Hippocampal Explicit Memory Is the Cornerstone for AGI
    Sangjun Park. ICML 2026. [Paper]

  2. From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
    Jinghao Luo, Yuchen Tian, Chuxue Cao, et al. ACL 2026. [Paper]

  3. Contextual Agentic Memory is a Memo, Not True Memory
    Binyan Xu, Xilin Dai, Kehuan Zhang. arXiv 2026. [Paper]

  4. Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
    Yanchen Wu, Tenghui Lin, Yingli Zhou, et al. arXiv 2026. [Paper]

  5. Multi-Agent Memory from a Computer Architecture Perspective: Visions and Challenges Ahead
    Zhongming Yu, Naicheng Yu, Hejia Zhang, et al. arXiv 2026. [Paper]

  6. Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
    Pengfei Du. arXiv 2026. [Paper]

  7. Position: Modular Memory is the Key to Continual Learning Agents
    Vaggelis Dorovatas, Malte Schwerin, Andrew D. Bagdanov, et al. arXiv 2026. [Paper]

  8. Rethinking Memory Mechanisms of Foundation Agents in the Second Half: A Survey
    Wei-Chieh Huang, Weizhi Zhang, Yueqing Liang, et al. arXiv 2026. [Paper] [Code]

  9. Graph-based Agent Memory: Taxonomy, Techniques, and Applications
    Chang Yang, Chuang Zhou, Yilin Xiao, et al. arXiv 2026. [Paper]

  10. The AI Hippocampus: How Far are We From Human Memory?
    Zixia Jia, Jiaqi Li, Yipeng Kang, et al. TMLR 2025. [Paper]

  11. Position Paper: MeMo: Towards Language Models with Associative Memory Mechanisms
    Fabio Massimo Zanzotto, Elena Sofia Ruzzetti, Giancarlo A. Xompero, et al. Findings of ACL 2025. [Paper]

  12. Lifelong Learning of Large Language Model based Agents: A Roadmap
    Junhao Zheng, Chengming Shi, Xidi Cai, et al. IEEE TPAMI 2025. [Paper]

  13. A Survey on the Memory Mechanism of Large Language Model based Agents
    Zeyu Zhang, Xiaohe Bo, Chen Ma, et al. ACM TOIS 2025. [Paper] [Code]

  14. AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents
    Jiafeng Liang, Hao Li, Chang Li, et al. arXiv 2025. [Paper]

  15. Memory in the Age of AI Agents
    Yuyang Hu, Shichun Liu, Yanwei Yue, et al. arXiv 2025. [Paper] [Code]

  16. Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences
    Andrew Kyle Lampinen, Martin Engelcke, Yuxuan Li, et al. arXiv 2025. [Paper]

  17. Procedural Memory Is Not All You Need: Bridging Cognitive Gaps in LLM-Based Agents
    Schaun Wheeler, Olivier Jeunen. arXiv 2025. [Paper]

  18. Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics
    Yiming Du, Wenyu Huang, Danna Zheng, et al. arXiv 2025. [Paper] [Code]

  19. From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs
    Yaxiong Wu, Sheng Liang, Chen Zhang, et al. arXiv 2025. [Paper]

  20. Cognitive Memory in Large Language Models
    Lianlei Shan, Shixian Luo, Zezhou Zhu, et al. arXiv 2025. [Paper]

  21. Episodic memory in AI agents poses risks that should be studied and mitigated
    Chad DeChant. arXiv 2025. [Paper]

  22. Cognitive Architectures for Language Agents
    Theodore R. Sumers, Shunyu Yao, Karthik Narasimhan, Thomas L. Griffiths. TMLR 2024. [Paper] [Code]

  23. Human-inspired Perspectives: A Survey on AI Long-term Memory
    Zihong He, Weizhe Lin, Hao Zheng, et al. arXiv 2024. [Paper]

⬆️ top

4. Frameworks, Products, and Resources

Paper-backed implementations are linked beside their papers above. The following broader platforms and curated collections were used as complementary sources and are useful for continued tracking.

  1. MemoryData
    OpenDataBox. [GitHub]

  2. Agent Memory Paper List
    Shichun-Liu. [GitHub]

  3. Awesome AI Memory
    IAAR-Shanghai. [GitHub]

  4. Awesome Memory for Agents
    TsinghuaC3I. [GitHub]

  5. Awesome Agent Memory
    TeleAI-UAGI. [GitHub]

  6. Awesome Graph-based Agent Memory
    DEEP-PolyU. [GitHub]

  7. Awesome Agent Memory Papers
    yyyujintang. [GitHub]

  8. Awesome Agent Memory (Foundation Agents)
    AgentMemoryWorld. [GitHub]

  9. MemTether
    MemTether. [GitHub]

  10. GoodMemory
    hjqcan. [GitHub]

  11. Mnemoverse
    Mnemoverse. [GitHub] [Docs]

  12. deja-vu (Cross-Agent Coding Session Memory)
    vshulcz. [GitHub] [Docs]

  13. SynapCores (AI-Native Database with Agent Memory)
    SynapCores. [Website] [GitHub] [Docs]

  14. XERJ (Search Engine and Long-Term Memory for AI Agents)
    xerj-org. [GitHub] [Docs]

  15. Atris (Project Memory for Coding Agents)
    atrislabs. [GitHub] [Guide]

  16. agent-qa (Persistent Memidex App Memory of Verified QA Evidence)
    vostride. [Website] [GitHub] [Memory docs] FSL-1.1-ALv2.

  17. Memory Poisoning Lab (Local Memory-security Teaching Range)
    Rishabh Pande. [GitHub]

⬆️ top

Citation

@article{memoryasdata,
    title={Are We Ready For An Agent-Native Memory System?},
    author={Wei Zhou and Xuanhe Zhou and Shaokun Han and Hongming Xu and Guoliang Li and Zhiyu Li and Feiyu Xiong and Fan Wu},
    year={2026},
    journal={arXiv preprint arXiv:2606.24775},
    url={https://arxiv.org/abs/2606.24775}
}

Contributors

Thanks to everyone who has contributed to this project!