Memory-Augmented Agents

Follow this topic Ask about this topic

Memory-augmented agents study how AI systems can retain and use information beyond the current prompt or observation, helping them handle long tasks, partial observability, and changing user or world states. Approaches range from episodic, semantic, and procedural stores—often organized as graphs, event records, or compressed visual and action histories—to learned policies that decide what to write, retrieve, update, or forget. Work spans embodied control and navigation, GUI and web use, dialogue, coding, and research, with evaluations including RoboMemArena, RoboMME, GOAT-Bench, LongMemEval, and software-engineering benchmarks. A central tension is that more memory can improve transfer and continuity but also introduce stale or misleading evidence, interference, cost, privacy leaks, and persistent attacks, making selective retrieval and longitudinal safety evaluation important open problems.

Latest papers

349 papers64 papers in the last four weeks, up 60% on the four weeks before. 0.4% of all new papers.

Retrieval as Traversal: Value-Indexed Memory for Stateful Long-Context Agents
Oct 29, 2026Daniel Strauß, Zhenshan Bing, Alois KnollLong-Context Retrieval Memory-Augmented Agents
Technical University of Munich · Nanjing University
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
CaliMem: Search-Efficient Data Agent via Calibrated Memory
Oct 25, 2026Hanze Li, Athan Z. Li, Feiyang Kang +4Training Data Curation Memory-Augmented Agents
Virginia Tech · University of Southern California · Princeton University
Don't Forget What You Just Learned: Self-Directed Repair Turns Agent Mistakes Into Lasting Lessons
Oct 22, 2026Yuval Kansal, Karen Ullrich, Polina Kirichenko +4Self-Improving Agents LLM Self-Correction
Princeton University · Meta FAIR
ColaBench: Evaluating Memory-Guided Knowledge Acquisition in Personal Agents
Oct 22, 2026Wenjie Zhang, Zhichao Shi, Xuhui Jiang +4Memory-Augmented Agents Personal AI Agents
Jiangnan University, Wuxi, China · School of Advanced Interdisciplinary Sciences, UCAS, Beijing, China · State Key Lab of AI Safety, Institute of Computing Technology, CAS, Beijing, China +3
Externalise the Memory: A Pre-Registered Study of Where an Embodied Agent's Experience Should Live
Oct 21, 2026Cheng-Yin TuMemory-Augmented Agents Visuomotor Policy Learning
Nikon Research Corporation of America
Memory-Centric Continual Learning for AI Agents
Oct 21, 2026Dongfang Li, Zhuoen Chen, Bonian Jia +25Memory-Augmented Agents Lifelong Learning Agents
inr2action: Encoding Robot Episodes as Neural Implicit Representations for Recall and Action
Oct 20, 2026Leann Alhashishi, Christos Margadji, Sebastian William PattinsonLong-Term Memory for Embodied Agents Memory-Augmented Agents
Institute for Manufacturing, Department of Engineering, University of Cambridge · Matta Labs, 77 East Road, London, United Kingdom
MemDev-Bench: Does Memory Help Code Agents?Benchmarking Memory Systems over Real Repository Histories
Oct 20, 2026Guorui Chen, Tao Liu, Zhenzhen Huang +9Memory Agent Benchmarks Memory-Augmented Agents
Southeast University, Nanjing, China · Southern University of Science and Technology, Shenzhen, China · MemoraX AI, Shenzhen, China
MemT-1.0: Towards Memory-Native Evolution
Oct 19, 2026Zhiyu Li, Zeyu Zhang, Linyun Liu +71Memory-Augmented Language Models Persistent Memory for Language Models
ACE-Trader: Adversarial Co-Evolution for Generator-Critic Trading Systems
Oct 19, 2026Chang Zhou, Jiarun Zhou, Xingtong Yu +3Algorithmic Trading Memory-Augmented Agents
University of Science and Technology of China · The Chinese University of Hong Kong
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
PACE-Mem: Prefix-Aware Complementary Evidence for Multimodal Agents
Oct 17, 2026Shidu Ren, Rong-cheng Tu, Hang Zhou +1Memory-Augmented Agents Memory-Augmented Video Understanding
Shidu Ren is with the Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON M5S 3G4, Canada · Rong-cheng Tu is with the College of Computing and Data Science, Nanyang Technological University, Singapore 639798 · Hang Zhou is with the Department of Statistics and Operations Research and the School of Data and Information Science, The University of North Carolina at Chapel Hill, Chapel Hill, NC 27599 USA +1
Beyond Success Rate: Interventional Evaluation of Memory in Vision-Language-Action Systems
Oct 16, 2026Keyuan Luo, Yi Xie, Wanyun Ling +3Memory-Augmented Agents Long-Term Memory for Embodied Agents
Hainan Bielefeld University of Applied Sciences (BiUH) · Technical University of Munich · Technische Universität Berlin
SkyAgent: Revisable Target Memory for Continuous Aerial Search
Oct 16, 2026Kaibo Yang, Xingyu Wu, Enze Zhu +6Aerial Robotics UAV Navigation
Aerospace Information Research Institute, Chinese Academy of Sciences · Key Laboratory of Target Cognition and Application Technology (TCAT) · School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences +1
When to Forget: Risk-Controlled Context Adaptation for Long-Horizon Agents
Oct 16, 2026Chenle Chen, Yangbo Wei, Zhijie Zheng +6LLM Context Management Long-Horizon Agent Tasks
University of California, Los Angeles · Shanghai Jiao Tong University · Arizona State University +1
Value as Memory: Online Value-Guided Post-training for General Robot Policies
Oct 15, 2026Wenye Yu, Yijin Chen, Kaiyi Xiong +7Robotic RL RL Post-Training
Shanghai Jiao Tong University · Shanghai Innovation Institute · Noematrix Ltd.
Mem4Act: Learning Effective Latent Memory for Long-Horizon Robotic Manipulation
Oct 15, 2026Yun Zhang, Zhiyu Huang, Tianhui Cai +3Long-Horizon Robotic Manipulation Memory-Augmented Agents
University of California, Los Angeles · North Carolina State University
Reliable Knowledge Acquisition for Continual Learning Agents
Oct 15, 2026Yixu Huang, Jiaqi W. MaContinual Learning for LLM Agents Continual Learning
University of California, Davis · University of Illinois Urbana-Champaign
An Agentic Framework for Proactive Robots with Procedural Assistance Memory
Oct 15, 2026Dohyun Lee, Minho Park, Jeonghoon Park +5Proactive Assistance Assistive Robotics
KAIST AI
EvolvingBrain: An Adaptive Skill System for Multi-modal Agents Self-Evolution in Open Worlds
Oct 14, 2026Runxuan Liu, Jingqi Shi, Baoxin Wang +10Self-Evolving Agents Agent Skill Learning
Harbin Institute of Technology · iFLYTEK · Meituan +1
Physical Time as a Missing Dimension of Robot Policy Memory Dynamics
Oct 14, 2026Yushen Liang, Yue Peng, Baosheng Jin +6Robot Policy Learning Memory-Augmented Agents
New York University Shanghai, Shanghai, China · University of Electronic Science and Technology of China, Chengdu, China
Reflect After Failure: Brain-Inspired Self-Evolving Agents for Embodied Spatial Intelligence
Oct 14, 2026Xin Li, Xiaohuan Gu, Yifan Wang +6Embodied Spatial Reasoning Self-Evolving Agents
City University of Hong Kong · East China Normal University · University of Electronic Science and Technology of China +2
MMLA-RSI: Recursive Self-Improvement through RTT and RTMA
Oct 14, 2026Junyi Zou, Avrova DonzSelf-Improving Agents Recursive Self-Improvement
MMLA-org · Communication University of China (CUC), No. 1 Dingfuzhuang East Street, Chaoyang District, Beijing 100024, China
ECHOES: Seeing Beyond the Current Image via Recursive History Compression and Privileged On-Policy Distillation
Oct 14, 2026Tengda Guo, Jiawang Hu, Yifei Tao +4Long-Horizon Agent Tasks Memory-Augmented Agents
Tsinghua University · StepFun · Nanyang Technological University +2
HEM-Med: A Hierarchical Agentic Memory Framework for Safe Multi-Center Medication Recommendation
Oct 14, 2026Min Xiao, Jin Li, Shoujin Wang +3Medication Recommendation Clinical Decision Support
Key Laboratory of Computing Power Network and Information Security, Ministry of Education; Shandong Computer Science Center (National Supercomputer Center in Jinan); Qilu University of Technology (Shandong Academy of Sciences); Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing; Shandong Fundamental Research Center for Computer Science, Jinan, Shandong, China · University of Technology Sydney
DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding
Oct 14, 2026Boyuan Sun, Deshui Miao, Wenzhao Gao +8Streaming Video Understanding Video QA
VCIP, Nankai University · ByteDance Inc. · IQuest Research +1
Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory
Oct 14, 2026Minghao Guo, Qingyue Jiao, Xiujin Liu +77Multimodal Memory Memory-Augmented Agents
Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents
Oct 13, 2026Xiyang Wu, Zhichao Liu, Shengxin zhang +4Long-Horizon LLM Agents Long-Horizon Reasoning
University of Maryland · Google · MBZUAI
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

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

Retrieval as Traversal: Value-Indexed Memory for Stateful Long-Context Agents

Daniel Strauß, Zhenshan Bing, Alois Knoll

Technical University of Munich · Nanjing University

Long-Context Retrieval Memory-Augmented Agents

Open paper AskPDF arXiv

Long-context models repeatedly solve closely related retrieval problems. Attention or global retrieval can retain large stores, but each forward pass again searches for what matters. Recurrent compression avoids this search only by deciding earlier what information to preserve. Neither mechanism directly exploits that useful memories at neighbouring retrieval steps may substantially overlap. We propose an alternative in which retrieval is a persistent local traversal through an address space. We separate a memory's content from its address. Utility is defined by the information revealed by retrieving the content, while geometry determines only how cheaply that information can be reached. This leads to a cost-regularised indexing objective that preserves information value inside local neighbourhoods while charging for every memory made locally accessible. Its marginal-value form gives both attractive and exclusion pressures. Thus, complementary memories should be co-retrievable when the additional value exceeds retrieval cost, whereas redundant memories should not occupy the same retrieval set solely because they are individually useful. As a proof of principle, we test only the simplest fixed-geometry instance on MiniGrid Memory. A persistent local traversal head reaches

0.95

mean return after

0.59

M training steps with a five-token context, compared with

0.94

M for Gaussian absolute addressing and more than

2

M for categorical absolute addressing. The experiment does not test learned geometry or repeated retrieval. Instead, it motivates the hypothesis that stateful retrieval may be easier to learn than stateless. To test the full proposed method further experimentation is necessary.