Existing memory-augmented LLM agents store past experience exclusively in prompt space, as textual summaries or retrieved passages, while keeping model parameters frozen throughout a rollout. Such agents can \emph{look up} what they have seen but cannot \emph{learn from} it: their policy is unchanged by experience, and any information dropped from the context is permanently lost. We introduce \texttt{TMEM}, a self-evolving parametric memory framework in which the agent not only compresses history into explicit memory but also absorbs distilled supervision into fast LoRA weights $Δ_t$ via lightweight online updates, genuinely altering its future behavior within a single episode. We formalize this as an agentic decision process with fast-weight rollout dynamics: actions are sampled from $π_{θ_0+Δ_t}$, while extraction actions produce supervision that updates $Δ_t$ for subsequent decisions. This view makes the extraction policy directly optimizable by RL: training $θ_0$ improves not only task actions but also the quality of the data used for online LoRA adaptation. We further propose SVD-based initialization of the LoRA subspace to accelerate online convergence. Experiments on LoCoMo, LongMemEval-S, multi-objective search, and CL-Bench show that \texttt{TMEM} consistently outperforms summary-based and retrieval-based baselines across different model scales.
SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory
Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院);School of Intelligence Science and Technology, Peking University(北京大学智能科学与技术学校);School of Computer Science and Technology, Beijing Institute of Technology(北京理工大学计算机科学与技术学校)
MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs
Shanghai Jiao Tong University(上海交通大学);Shanghai Innovation Institute(上海创新研究院);National University of Singapore(新加坡国立大学);Xidian University(西安电子科技大学);University of Science and Technology of China(中国科学技术大学);MemTensor (Shanghai) Technology Co., Ltd.(MemTensor(上海)科技有限公司)
CHIME: Credit-Aware Hierarchical Memory Evolution for Long-Horizon Agentic Planning
Institute of Artificial Intelligence, Xiamen University(厦门大学人工智能学院);Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan (Xiamen University), Ministry of Culture and Tourism(文化和旅游部闽台非物质文化遗产数字化保护与智能处理重点实验室(厦门大学));Zhejiang University(浙江大学);Alibaba Group(阿里巴巴集团)
VideoEvolve: Co-Evolving Memory and Retrieval for Long Video Understanding
Alibaba Group(阿里巴巴集团);University of Science and Technology of China(中国科学技术大学);Shanghai Jiao Tong University(上海交通大学);University of Chinese Academy of Sciences(中国科学院大学);Beihang University(北京航空航天大学)
PhotoCraft: Agentic Reasoning with Hierarchical Self-Evolving Memory for Deep Image Search
Pattern Recognition Center, WeChat AI, Tencent Inc.(微信AI模式识别中心,腾讯公司);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Zhongguancun Academy(中关村学院);Nanyang Technological University(南洋理工大学);Shanghai Jiao Tong University(上海交通大学)
East China Normal University(华东师范大学);Shanghai Innovation Institute(上海创新研究院);Harbin Institute of Technology(哈尔滨工业大学);Xiamen University(厦门大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Independent Researcher(独立研究者)
PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft
Northwestern University(西北大学);Northeastern University(东北大学);South China University of Technology(华南理工大学);Hong Kong Baptist University(香港 Baptist大学);Beijing Normal - Hong Kong Baptist University(北京师范大学-香港 Baptist大学)
SEDM: Selective Self-Evolving Distributed Memory for Agents
Gradient Zhejiang University(Gradient浙江大学);Gradient South China University of Technology(Gradient南方科技大学);Gradient Waseda University(Gradient武藏大学);Gradient University of Toronto(Gradient多伦多大学);Gradient Rice University(Gradient里士满大学);Gradient Emory University(Gradient埃默里大学);Gradient University of Technology Sydney(Gradient悉尼技术大学)
MemScope: Evolving Agent Memory Architectures through Localized Code Repair
State Key Laboratory of AI Safety(人工智能安全国家重点实验室);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Meituan(美团)
University of Pennsylvania(宾夕法尼亚大学);Brown University(布朗大学);Nanyang Technological University(南洋理工大学);University of Notre Dame(圣母大学);George Mason University(乔治梅森大学)
ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval
Shenzhen International Center for Industrial and Applied Mathematics(深圳国际工业与应用数学中心);Shenzhen Research Institute of Big Data(深圳大数据研究院);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Shenzhen Campus of Sun Yat-sen University(中山大学深圳校区);Shenzhen Loop Area Institute(深圳河套学院)
RGMem: Renormalization Group-inspired Memory Evolution for Language Agents
School of Computer Science;Engineering, Beihang University, Beijing, China;School of Reliability;Systems Engineering, Beihang University, Beijing, China;State Key Laboratory of Complex \& Critical Software Environment;National Key Laboratory of Reliability;State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences
Personalized Large Language Model Assistant with Evolving Conditional Memory
The Hong Kong Polytechnic University(香港理工大学);INF Technology (Shanghai) co., Ltd.(INF科技(上海)有限公司);Institute of Artificial Intelligence, Soochow University, China(苏州大学人工智能研究院)
MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
Nanyang Technological University(南洋理工大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of Illinois Chicago(伊利诺伊大学芝加哥分校);Tsinghua University(清华大学)
EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective
Hong Kong University of Science and Technology (Guangzhou)(香港理工大学(广州));Createlink Technology(创-link科技);Beijing University of Posts and Telecommunications(北京邮电大学);Beijing Institute of Technology(北京理工大学)