Agent Memory Management

Follow this topic Ask about this topic

It gives language and embodied agents persistent state beyond a context window, supporting personalization, multi-step work, and adaptation as facts change. Systems range from raw-log and vector-search stores to episodic-semantic hierarchies, temporal or provenance-aware graphs, and learned controllers that decide what to write, retrieve, consolidate, or discard. Evaluations use long-dialogue question answering benchmarks such as LoCoMo and LongMemEval, alongside tool-use, coding, and GUI tasks, measuring accuracy as well as token cost, latency, retention, and stale or unsafe recall. The central challenge is balancing useful evidence and traceability against bounded storage and computation: retention cannot help if retrieval fails, while compression, updates, and sharing can lose, stale, or expose information, and no design works best across all workloads.

Latest papers

449 papers68 papers in the last four weeks, up 8% on the four weeks before. 0.4% of all new papers.

Useful Memories Become Faulty When Continuously Updated by LLMs
May 13, 2026Dylan Zhang, Yanshan Lin, Zhengkun Wu +4AI Agent Reliability Persistent Memory for Language Models
University of Illinois Urbana-Champaign · IIIS, Tsinghua University
LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues
May 12, 2026Di Wu, Zixiang Ji, Asmi Kawatkar +4Computer-Use Agent Benchmarks Retrieval-Augmented Generation
University of California, Los Angeles
$δ$ -mem: Efficient Online Memory for Large Language Models
May 12, 2026Jingdi Lei, Di Zhang, Junxian Li +7Memory-Augmented Language Models Memorization in Language Models
Nanyang Technological University · Mind Lab · Fudan University +3
PRISM: Pareto-Efficient Retrieval over Intent-Aware Structured Memory for Long-Horizon Agents
May 12, 2026Jingyi Peng, Zhongwei Wan, Weiting Liu +1Graph-Based Retrieval Information Retrieval
Singapore Management University · The Ohio State University · Fudan University
SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory
May 12, 2026Juntong Wang, Haoyue Zhao, guanghui Pan +4Agent Memory Graph Retrieval-Augmented Generation
Institute for Artificial Intelligence, Peking University · School of Intelligence Science and Technology, Peking University · School of Computer Science and Technology, Beijing Institute of Technology
Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory
May 11, 2026Mingxi Zou, Zhihan Guo, Langzhang Liang +6Rate-Distortion Theory Long-Term Conversational Memory
Fudan University · The Chinese University of Hong Kong · Meta AI +3
MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs
May 11, 2026Ruiyi Yang, Zechen Li, Hao Xue +2Agent Memory Continual Learning for LLM Agents
University of New South Wales · The Hong Kong University of Science and Technology (Guangzhou) · Mohamed Bin Zayed University of Artificial Intelligence
Bridging the Cognitive Gap: A Unified Memory Paradigm for 6G Agentic AI-RAN
May 11, 2026Xijun Wang, Zhaoyang Liu, Chenyuan Feng +36G Networks Wireless Communications
Sun Yat-sen University, China · University of Exeter, U.K. · Zhejiang University, China +2
PREPING: Zero-Task Agent Memory Construction via Self-Practice
May 11, 2026Yumin Choi, Sangwoo Park, Minki Kang +2Agent Memory Synthetic Data Generation
KAIST
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
May 11, 2026Dongming Jiang, Yi Li, Guanpeng Li +2Agent Memory Graph-Based Agent Memory
Department of Computer Science, The University of Texas at Dallas · Department of Electrical and Computer Engineering, University of Florida · University of California, Davis
Portable Agent Memory: A Protocol for Cryptographically-Verified Memory Transfer Across Heterogeneous AI Agents
May 10, 2026Santhosh Kumar RavindranAgent Memory Persistent Memory for Language Models
Microsoft Corporation, Redmond, WA, USA
MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents
May 10, 2026Yining Chen, Jihao Zhao, Bo Tang +5Agent Memory Privacy-Preserving ML
1MemTensor (Shanghai) Technology Co., Ltd. · 3Tongji University · 2HONOR Device Co., Ltd.
EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium
May 10, 2026Yuqiao Meng, Luoxi Tang, Sakshi Sunil Narvekar +4Multi-Agent Debate Agent Memory Poisoning
Binghamton University, State University of New York, Binghamton, NY, USA · University of Iowa, Iowa City, IA, USA
Human-Inspired Memory Architecture for LLM Agents
May 8, 2026Doga Kerestecioglu, Alexei Robsky, Clemens Vasters +2Agent Memory Management LLM Agent Memory
Microsoft
MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs
May 8, 2026Junwei Liao, Haoting Shi, Ruiwen Zhou +9LLM Agent Memory Q-Learning
Shanghai Jiao Tong University · Shanghai Innovation Institute · National University of Singapore +3
MemCompiler: Compile, Don't Inject -- State-Conditioned Memory for Embodied Agents
May 8, 2026Xin Ding, Xinrui Wang, Yifan Yang +9Embodied AI Memory-Augmented Agents
University of Science and Technology of China · Huazhong University of Science and Technology · Microsoft Research +2
MEMOREPAIR: Barrier-First Cascade Repair in Agentic Memory
May 8, 2026Yang Zhao, Chengxiao Dai, Mengying Kou +1Agent Memory Management
STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
May 7, 2026Hanxiang Chao, Yihan Bai, Rui Sheng +2Agent Memory LLM Agent Evaluation
Wuhan University1, Wuhan, China1 · The Hong Kong University of Science and Technology3, Hong Kong, China23 · The Chinese University of Hong Kong2, Hong Kong, China23
Storage Is Not Memory: A Retrieval-Centered Architecture for Agent Recall
May 6, 2026Joshua Adler, Guy ZehaviAgent Memory LLM Agent Memory
Sauron Labs
Governed Collaborative Memory as Artificial Selection in LLM-Based Multi-Agent Systems
May 5, 2026Diego F. Cuadros, Abdoul-Aziz Maiga, Helen Meskhidze +1Multi-Agent LLM Systems LLM Agent Memory
Digital Epidemiology Laboratory, Digital Futures, University of Cincinnati, Cincinnati, OH, USA · Department of Biological Sciences, University of Cincinnati, Cincinnati, OH, USA · Center for Humanities and Technology (CHaT), University of Cincinnati, Cincinnati, OH, USA +2
ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting
May 5, 2026Jiale Chang, Yuxiang RenMultimodal Memory LLM Agent Memory
Nanjing Agricultural University · Nanjing University
MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents
May 5, 2026Bronislav Sidik, Lior RokachLLM Agent Memory Hierarchical Memory
Institute for Applied AI Research · Faculty of Computer and Information Science · Ben-Gurion University of the Negev, Beer Sheva, Israel
MemFlow: Intent-Driven Memory Orchestration for Small Language Model Agents
May 5, 2026Jiayi Chen, Yingcong Li, Guiling WangLLM Agent Workflow Optimization Persistent Memory for Language Models
New Jersey Institute of Technology, Newark, USA
Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory
May 4, 2026Yuhui Wang, Tanqiu Jiang, Jiacheng Liang +2LLM Agent Security Agent Memory Management
Stony Brook University USA · Cisco Systems USA
MEMAUDIT: An Exact Package-Oracle Evaluation Protocol for Budgeted Long-Term LLM Memory Writing
May 4, 2026Nishant Bhargava, Rodrigo Sobral BarrentoPersistent Memory for Language Models LLM Agent Evaluation
Purdue University
GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory
May 3, 2026Yushi Sun, Bowen Cao, Dong Fang +2LLM Agent Memory Persistent Memory for Language Models
LIGHTSPEED, Shenzhen, China · The Chinese University of Hong Kong, Hong Kong, China
Feedback-Normalized Developer Memory for Reinforcement-Learning Coding Agents: A Safety-Gated MCP Architecture
May 2, 2026Mehmet IscanMemory-Augmented Agents Agent Memory Management
PythaLab, Yildiz Technical University, Istanbul, Türkiye
MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents
May 2, 2026Hung Pham Van, Nguyen Manh Hieu, Khang Pham Tran Tuan +4Conversational Memory Graph Retrieval-Augmented Generation
1Independent Researcher · 2Hanoi University of Science and Technology · 3VNU University of Engineering and Technology +1
Beyond Compaction: Structured Context Eviction for Long-Horizon Agents
May 1, 2026Andrew Semenov, Svyatoslav DorofeevLong-Horizon LLM Agents LLM Context Management
Kiz8
Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory
May 1, 2026Derong Xu, Shuochen Liu, Pengfei Luo +8Memorization in Language Models Memorization in Generative Models
University of Science and Technology of China & State Key Laboratory of Cognitive Intelligence · City University of Hong Kong · Dalian University of Technology +1

May 13, 2026J/K move · Enter open · S save

Useful Memories Become Faulty When Continuously Updated by LLMs

Dylan Zhang, Yanshan Lin, Zhengkun Wu, Yihang Sun+3

University of Illinois Urbana-Champaign · IIIS, Tsinghua University

AI Agent Reliability Persistent Memory for Language Models Episodic Memory Agent Memory Management LLM Agent Reliability Memory Consolidation+2

Open paper AskPDF arXiv

Learning from past experience benefits from two complementary forms of memory: episodic traces -- raw trajectories of what happened -- and consolidated abstractions distilled across many episodes into reusable, schema-like lessons. Recent agentic-memory systems pursue the consolidated form: an LLM rewrites past trajectories into a textual memory bank that it continuously updates with new interactions, promising self-improving agents without parameter updates. Yet we find that such consolidated memories produced by today's LLMs are often faulty even when derived from useful experiences. As consolidation proceeds, memory utility first rises, then degrades, and can fall below the no-memory baseline. More surprisingly, even when consolidating from ground-truth solutions, GPT-5.4 fails on 54% of a set of ARC-AGI problems it had previously solved without memory. We trace the regression to the consolidation step rather than the underlying experience: the same trajectories yield qualitatively different memories under different update schedules, and an episodic-only control that simply retains those trajectories remains competitive with the consolidators we test. In a controlled ARC-AGI Stream environment that exposes Retain, Delete, and Consolidate actions, agents preserve raw episodes by default and double the accuracy of their forced-consolidation counterparts; disabling consolidation entirely (episodic management only) matches this auto regime. Practically, robust agent memory should treat raw episodes as first-class evidence and gate consolidation explicitly rather than firing it after every interaction. Looking forward, reliable agentic memory will require LLMs that can consolidate without overwriting the evidence they depend on.