Choosing How to Remember: Adaptive Memory Structures for LLM Agents
University of Technology Sydney(悉尼大学);University of Texas at Austin(德克萨斯大学奥斯汀分校);University of California, Los Angeles(加州大学洛杉矶分校);The University of Melbourne(墨尔本大学)
Memory is critical for enabling large language model (LLM) based agents to maintain coherent behavior over long-horizon interactions. However, existing agent memory systems suffer from two key gaps: they rely on a one-size-fits-all memory structure and do not model memory structure selection as a context-adaptive decision, limiting their ability to handle heterogeneous interaction patterns and resulting in suboptimal performance. We propose a unified framework, FluxMem, that enables adaptive memory organization for LLM agents. Our framework equips agents with multiple complementary memory structures. It explicitly learns to select among these structures based on interaction-level features, using offline supervision derived from downstream response quality and memory utilization. To support robust long-horizon memory evolution, we further introduce a three-level memory hierarchy and a Beta Mixture Model-based probabilistic gate for distribution-aware memory fusion, replacing brittle similarity thresholds. Experiments on two long-horizon benchmarks, PERSONAMEM and LoCoMo, demonstrate that our method achieves average improvements of 9.18% and 6.14%.
Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning
Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS)(智能信息处理重点实验室,计算技术研究所,中国科学院);Key Laboratory of AI Safety, Chinese Academy of Sciences(人工智能安全重点实验室,中国科学院);University of Chinese Academy of Sciences, Beijing, China(中国科学院大学,北京,中国);Li Auto Inc.(利亚德公司)
The Right to Be Remembered: Preserving Maximally Truthful Digital Memory in the Age of AI
Insilico Medicine AI Limited(英矽智能人工智能有限公司);Insilico Medicine US Inc(英矽智能美国公司);Insilico Medicine Hong Kong Ltd.(英矽智能香港有限公司);Duke University(杜克大学);Duke Kunshan University(昆山杜克大学);University of Louisville(路易斯维尔大学)
Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory
Institute of Automation, CAS(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);Zhongguancun Academy(中关村学院);Zhongguancun Institute of Artificial Intelligence(中关村人工智能研究所);Department of Gastrointestinal Surgery, Fujian Provincial Cancer Hospital(福建省癌症医院胃肠外科);College of Computer and Data Science, Fuzhou University(福州大学计算机与数据科学学院)
Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
AGI Institute, School of Computer Science, Shanghai Jiao Tong University(AGI研究院,计算机科学学院,上海交通大学);Tongyi Lab, Alibaba Group(通义实验室,阿里巴巴集团);Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University(上海市教育委员会智能交互与认知工程重点实验室,上海交通大学)
Learning What to Remember and What to Internalize in LLM Self-Evolution via Adaptive Memory-Parameter Coordination
University of Science and Technology of China(中国科学技术大学);City University of Hong Kong(香港城市大学);Hefei Normal University(合肥师范学院);Xi’an Jiaotong University(西安交通大学)
Watch, Remember, Reason: Human-View Video Understanding with MLLMs
School of Intelligence Science and Technology, Peking University(北京理工大学智能科学与技术学院);Wuhan University(武汉大学);Shanghai Jiao Tong University(上海交通大学);Nanyang Technological University(南洋理工大学);CASIA(中国科学院自动化研究所);University of Tokyo(东京大学);University of Liverpool(利物浦大学);Zhejiang University(浙江大学);National University of Singapore(新加坡国立大学);UC Merced(加州大学默塞德分校)
Evo-MedAgent: Beyond One-Shot Diagnosis with Agents That Remember, Reflect, and Improve
Technical University of Munich(慕尼黑技术大学);TUM University Hospital(TUM大学医院);LMU Munich(慕尼黑大学);National University of Singapore(新加坡国立大学);Munich Center for Machine Learning(慕尼黑机器学习中心);Imperial College London(伦敦帝国理工学院)
Verses Research Lab(Verses研究实验室);DeepMind(深度思维);Google Research(谷歌研究院);University College London(伦敦大学学院);University of Toronto(多伦多大学);University of Berkeley, California(加州大学伯克利分校)
Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory
Fudan University(复旦大学);The Chinese University of Hong Kong(香港中文大学);Meta AI;AI Research Institute, Squirrel Ai Learning(Squirrel Ai Learning人工智能研究院);Monash University(墨尔本大学);Shanghai Academy of AI for Science(上海人工智能科学研究院)
Concept Learning through Deep Reinforcement Learning with Memory-Augmented Neural Networks
Institute of Automation, Chinese Academy of Sciences (CASIA)(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);Center for Excellence in Brain Science and Intelligence Technology, CAS(中国科学院脑科学与智能技术卓越创新中心)
ReCAT: Remember, Count, and Time: Structured Recurrent Memory for Robot Manipulation
University of Edinburgh(爱丁堡大学);Intuitive Robots Lab, Karlsruhe Institute of Technology (KIT)(卡尔斯鲁厄理工学院直觉机器人实验室);NVIDIA(英伟达);Robotics Institute Germany (RIG)(德国机器人研究所)
MemoWM: How World Models Change What Agents Need to Remember
South China University of Technology(华南理工大学);University of the Chinese Academy of Sciences(中国科学院大学);Beijing University of Posts and Telecommunications(北京邮电大学);University of Science and Technology of China(中国科学技术大学);Tsinghua University(清华大学);Peking University(北京大学);Fudan University(复旦大学);Shanghai Jiao Tong University(上海交通大学)
Back to Basics: Let Conversational Agents Remember with Just Retrieval and Generation
The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州));The Hong Kong University of Science and Technology(香港科学与技术大学);National University of Singapore(新加坡国立大学)