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

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

MemSteer: Turning User Histories into Supervision for Agent Memory Optimization
Oct 29, 2026Jie Huang, Cuiling Lan, Qize Yu +2LLM Agent Memory Agent Memory Management
Peking University · Microsoft Research Asia
Adaptive Memory Index Evolution for Agents
Oct 26, 2026Yuntong Hu, Tongli Su, Yuanfu Sun +3Agent Memory Agent Memory Management
Emory University · New York University · Meituan
Let Them Sleep: Recursive Self-Pruning Memory for Long-Horizon LLM Agents
Oct 18, 2026Kargi Chauhan, Sadiba Nusrat Nur, Pratibha Revankar +2Memory Consolidation for LLM Agents LLM Agent Memory
University of California, Santa Cruz
MemDerive: A Diagnostic Benchmark for Agent Memory over Evolving Data
Oct 18, 2026Sen Gao, Yongan Li, Han Chen +5Agent Memory Memory Agent Benchmarks
National University of Singapore, Singapore, Singapore · Shanghai Jiao Tong University, Shanghai, China · Zero Gravity Labs, Singapore, Singapore
Memories That Outlive Their Reasons: Dependency-Tethered Memory for Tool-Using LLM Agents
Oct 18, 2026Yiqi Wang, Jinqian Ju, Jiaqi Zhang +5LLM Agent Memory Memory-Augmented Agents
University of Southern Queensland Australia · Southern University of Science and Technology China · Jiangsu University China +3
Spatial Memory by Agents, for Agents
Oct 15, 2026Qianwei Wang, Ce Zhang, Zhanpeng Luo +3Robotic Spatial Memory Agent Memory
Qianwei Wang is with Princeton University · Ce Zhang is with Carnegie Mellon University · Zhanpeng Luo is with Johns Hopkins University +2
Memorizing Who, Knowing How: Benchmarking Personal and Procedural Memory for Persistent Assistants
Oct 14, 2026Maosheng Qin, Qi Zhang, Mingxuan Xia +5Agent Memory Persistent Memory for Language Models
Zhejiang University · Ant Group
When Agent Memory Needs to Compute: Evidence Access and Executable Aggregation
Oct 14, 2026Zerui Yang, Quan Xue, Chaorui Zhang +8Agent Memory Agent Memory Management
Huawei Technologies Ltd.
MemCode: Discrete Semantic Representations for Long-Term Agent Memory
Oct 14, 2026Xin Li, Liang Hu, Duoqian Miao +2LLM Agent Memory Memory Management for LLM Agents
Tongji University · WorldMind
STRATA: Self-Maintaining Structured Experience Graphs for Self-Evolving Language Agents
Oct 14, 2026Guanhua Zhu, Hanwen Li, Zhi Wei +2LLM Agent Self-Improvement Agent Memory Management
Department of Informatics, New Jersey Institute of Technology · Department of Computer Science, New Jersey Institute of Technology · School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen
Knowing the User Is Not Knowing What We Established: Grounding Awareness in Personal Agents
Oct 13, 2026Jiajun Chen, Xinyue Chen, Yicheng Jiang +1Personal AI Agents AI Agent Reliability
Carnegie Mellon University · New York University · NYU Shanghai
Learning How to Remember: Memory Modality Selection for GUI Agents
Oct 13, 2026Taeyun Roh, Suhyeong Park, Gijin Kim +2Memory-Augmented Agents GUI Agents
Korea University · Myongji University · AIGEN Sciences
Memory Echo in Single-Agent Long-Term Memory: Lifecycle Evaluation and Provenance-Guided Mitigation
Oct 13, 2026Yufeng Li, Sheng Yao, Peng Zeng +5Agent Memory Management Long-Term Conversational Memory
East China Normal University, Shanghai, China · University of Southern California, Los Angeles, USA · Zhejiang University, Hangzhou, China +1
StateHarness: Maintaining Evolving Project State for Long-Horizon Coding Agents
Oct 13, 2026Chuan Zou, Yujun Zhou, Xiaonan Luo +1Software Engineering Agents State Tracking
University of Pennsylvania · University of Notre Dame
Many Steps into One: Reasoning Contraction and the Limits of Safe Memory Reuse for LLM Agents
Oct 13, 2026Jianghong Zhou, Hao Rong, Chen Lin +1Agent Memory Management LLM Agent Safety
1ByteDance · 2Scale AI
VitaBench: Memory Lifecycles Beyond Retrieval
Oct 10, 2026Muquan Yu, Dihan HuMemory Agent Benchmarks Agent Memory Management
University of Hong Kong · Chinese University of Hong Kong · Cornell University
Event-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational Agents
Oct 8, 2026Yichen Liu, Chunfeng Yuan, Haowei Liu +5Long-Term Conversational Memory Agent Memory Management
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China · Beijing Key Laboratory of Super Intelligent Security of Multi-Modal Information, Beijing, China +4
DeltaReplay: Task-Relative Memory Reuse for Mobile GUI Agents
Oct 8, 2026Yudong Bai, Yihong Chen, Quanming Yao +1Mobile GUI Agents Agent Memory Management
Tsinghua University
Gated Memory: Admission-Controlled Memory Formation for Conversational AI
Oct 8, 2026Preeti Saraswat, Divya Neelagiri, Ajay ManojConversational Memory Long-Term Conversational Memory
Samsung Research America, Mountain View, CA
What to Admit and How to Present: Governing Persistent Memory in LLM Agents
Oct 8, 2026Chang Liu, Deliang DingAgent Memory Management Persistent Memory for Language Models
Pazhou Laboratory Guangzhou, China
MemoWM: How World Models Change What Agents Need to Remember
Oct 7, 2026Bingfan Zeng, Zhisheng Chen, Chenbo Sang +6Memory Compression Agent Memory Management
South China University of Technology · University of the Chinese Academy of Sciences · Beijing University of Posts and Telecommunications +5
Stale, Misattributed, or Late: Where Personal Memory Fails Before Generation
Oct 7, 2026Haonan Deng, Park SinchaisriAgent Memory Agent Memory Management
University of California, Berkeley · Haas School of Business, University of California, Berkeley
HGP:An on-device personalized agent memory via hybrid graph storage
Oct 7, 2026Ran Zhou, Xueming Han, Jiaheng Liu +4Agent Memory Agent Memory Management
School of Intelligence Science and Technology, Nanjing University · Jiutian Research
Relevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QA
Oct 7, 2026Yufeng Li, Shuxin Li, Zhenhua Xu +7Long-Term Conversational Memory Agent Memory Management
East China Normal University, Shanghai, China · Nanyang Technological University, Singapore · Zhejiang University, Hangzhou, China +3
Whose Memory Is It? Scope-Aware Commit Rules for Long-Term LLM Memory
Oct 6, 2026Hongyu Gu, Xinchang LiLong-Term Conversational Memory Agent Memory Management
University of Science and Technology of China Hefei, China
Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice
Oct 6, 2026Jan-Peter FrankeLLM Context Management Agent Memory Management
Münster, Germany
Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus
Oct 6, 2026Egor Pakhomov, Erik NijkampLong-Horizon Agent Evaluation Agent Memory Management
Salesforce AI Research
MINDSET: Energy-based Schema Evolution for Long Conversational Agent Memory
Oct 6, 2026Sujato Dutta, Sreekruthy Tummala, Shashank Vanga +1Long-Term Conversational Memory Agent Memory Management
Mahindra University
AgentMemGate: Addressing Speculation Contamination in Conversational Assistant Memory
Oct 6, 2026Chirag Sharma, Benjamin Fowlersmith, Karime MaamariConversational Memory Long-Term Conversational Memory
Distyl AI
Understanding and Mitigating Inference-Time Overreliance Using Agentic Memory
Oct 5, 2026Luoxi Tang, Yuqiao Meng, Nilesh Auradkar +3Agent Memory LLM Memory
Binghamton University, State University of New York, Binghamton, NY, USA · University of Iowa, Iowa City, IA, USA · Penn Medicine, University of Pennsylvania, Philadelphia, PA, USA

Oct 29, 2026J/K move · Enter open · S save

MemSteer: Turning User Histories into Supervision for Agent Memory Optimization

Jie Huang, Cuiling Lan, Qize Yu, Xiulian Peng+1

Peking University · Microsoft Research Asia

LLM Agent Memory Agent Memory Management Synthetic Data Generation for Language Models

Open paper AskPDF arXiv

An effective agent memory system should adapt to a user's history and task requirements. Human-annotated supervision can guide this adaptation by providing feedback for evaluating and improving memory designs. Yet suitable labels are rarely available for new user histories, and manually constructing QA pairs and supporting evidence is costly. We introduce MemSteer, which turns unlabeled user histories into question-answer (QA) supervision with supporting evidence for memory-design optimization. MemSteer constructs an evidence-grounded answer plan that specifies how facts across related records jointly support a reference answer. The plan guides question generation, while source-grounded auditing and blind answer recovery check the resulting annotations. To study the utility of this supervision, we develop MemSteer-Opt, which combines QA-based design evaluation with evidence-guided failure diagnosis to revise memory store, retrieval, and context construction without updating model parameters. Experiments on ATM-Bench and RHELM show that this supervision is competitive with official-QA-guided optimization. Relative to Base-BM25, MemSteer-Opt improves ATM-Bench Question Score by 13.4 points and RHELM accuracy by 4.1 and 6.6 points without and with external data, respectively. The supervision also benefits two existing optimizers on ATM-Bench, while new-user experiments demonstrate continued design optimization using supervision generated from the target histories.