Memory-Augmented Language Model Agents

Follow this topic Ask about this topic

Momentum

50 papers in the last four weeks, up 233% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 275

All topics

Self-Designed Evaluators and Warm Memory for Long-Horizon Agents
Sep 27, 2026Saeid Asgari, Emre Kiciman, Leonardo de Oliveira Nunes +1Language Model Generation Evaluation Long-Horizon Agent Evaluation
Microsoft
NLPG: Natural-Language Policy Gradients for Self-Evolving Language Agents
Sep 27, 2026Xu Liu, WenZhang Wei, Jun Cao +4Continual Learning for LLM Agents Policy Optimization
School of Electronic Information, Wuhan University, Wuhan 430079, China · School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China · State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China
LSTMem: Hierarchical Long Short-Term Online Memory for Large Language Models
Sep 27, 2026Xianglong Shi, Ruijie Yang, Sirui Zhao +4Memory-Augmented Language Models Persistent Memory for Language Models
University of Science and Technology of China
Decision-Sufficient State Representations: Measuring and Reducing Write-Time Regret
Sep 26, 2026Bingyu Shen, Boyang LiState Tracking State Representation Learning
Independent Researcher · Department of Computer Science and Technology Kean University, Union, NJ, USA
Adaptive Consistency Graph for Long-Horizon Agents
Sep 26, 2026Jiecong Wang, Hao Peng, Zhanyi WangLong-Horizon Agent Evaluation Graph-Based Agent Memory
Beihang University · QI-ANXIN GROUP
SCLATE: a Substrate for Continual-Learning Agent Training and Evaluation
Sep 26, 2026Youngmok Jung, Sirajul Salekin, Henry Tran +3Continual Learning for LLM Agents Long-Horizon Agent Evaluation
Apple
IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis
Sep 24, 2026Xingyu Wu, Yuchen Yan, Zhengxi Lu +9Long-Horizon LLM Agents RL for LLM Agents
Zhejiang University · Tencent
ADM-Planner: LLM-Guided Long-Horizon Planning for Mobile Manipulators with Attention-Enhanced Dynamic Memory
Sep 24, 2026Jiaping Xiao, Pingyuan Ji, Mir FeroskhanLong-Horizon Robotic Manipulation Mobile Manipulation
School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore
Agent Memory with Episodic Retrieval for Financial Decision-Making
Sep 23, 2026Nuoyue Xu, Jiang Liu, Wenxuan Huang +3Multi-Agent LLM Systems LLM Agent Memory
University of British Columbia · University of Science and Technology of China · Fudan University +1
Learning from Failures: Heterogeneous Graph Memory for Small Language Model Tool-Using Agents
Sep 23, 2026Jiaxing Li, Lei Song, Rui Dong +1Graph-Based Agent Memory Long-Horizon LLM Agents
School of Computer Science and Engineering, Southeast University, Nanjing, China
ChipMEM: Verification-Grounded Memory for EDA Agents
Sep 22, 2026Abdulrahman AlRabah, Joshua Mabry, Dilek Hakkani-Tür +4Electronic Design Automation LLM Agent Skill Learning
University of Illinois Urbana-Champaign · NVIDIA · Cadence
From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Health
Sep 21, 2026He Hu, Yucheng Zhou, Qianning Wang +8Personalized Language Models Medical LLMs
TTSE: A Two-Track Online Self-Evolution Framework
Sep 21, 2026Ruimin Pei, Yongkang Wu, Shangyi Zheng +5LLM Agent Self-Improvement Agent Skill Learning
Poisson Lab, Huawei China
An Architecture for Long-Horizon Agents: Levels, Ticks and Cascaded Intelligence
Sep 17, 2026Erik Nijkamp, Anurag Koul, Egor Pakhomov +1Cognitive Architectures for AI Agents Continual Learning for LLM Agents
Salesforce AI Research
Rollback the World, Keep the Reflection: Rollback-Induced Reflection for Long-Horizon LLM Agents
Sep 16, 2026Yi Yu, Liuyi Yao, Yaliang Li +2Long-Horizon LLM Agents LLM Agent Reliability
Wuhan University · Alibaba Group
Interactive Memory Learning for Long-Term Conversations
Sep 15, 2026Cai Ke, Jiangyue Yan, Han Zhang +5Multi-Agent LLM Systems Long-Term Conversational Memory
Harbin Institute of Technology, Shenzhen, China · Pengcheng Laboratory, China
ThinkFlow: Self-Evolving Probabilistic Latent Memory for Lifelong Conversational Agents
Sep 15, 2026Cai Ke, Xin Liu, Han Zhang +6Test-Time Adaptation Lifelong Learning Agents
Pengcheng Laboratory, China · Harbin Institute of Technology, Shenzhen, China · China Unicom Greater Bay Area Innovation Institute, China
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments
Sep 14, 2026Sibo Zhu, Shicheng Fan, Xinyue Wang +3Multi-Agent LLM Systems LLM Agent Self-Improvement
Aether AI · University of California San Diego · ‡Work done during internship in Aether AI +1
EMR: Self-Evolving Medical Multi-Agent System via Experience Mining and Reuse
Sep 14, 2026Dongsheng Shi, Yue Li, Xin Yi +1Continual Learning for LLM Agents Multi-Agent LLM Systems
East China Normal University · City University of Hong Kong
CoMem: Collective-Individual Memory Synergy for Evolutionary Multi-Agent Systems
Sep 14, 2026Chengxin Yu, Zhaoxin Fan, Faguo Wu +3Multi-Agent LLM Systems Multi-Agent Collaboration
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, School of Artificial Intelligence, Beihang University · Beijing academy of blockchain and edge computing · National University of Defense Technology +1
LifeMem: Enabling Lifelong Experience Reuse for LLM Agents
Sep 14, 2026Yuli Qiu, Yutong Li, Wei Su +5Continual Learning for LLM Agents LLM Agent Skill Learning
School of Computer Science and Technology, Beijing Institute of Technology · School of Computer Science and Engineering, Beihang University · Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology +1
MemRiskBench: Trace-Aware Risk-Preserving Evaluation for Long-Horizon LLM Agents
Sep 14, 2026Jianhua Jiang, Dongbo Yuan, Weihua LiLong-Horizon Agent Evaluation AI Agent Safety Benchmarks
School of Artificial Intelligence and Computer Science, Jilin University of Finance and Economics, 130117 Changchun, China · Jilin Province Key Laboratory of Fintech, Jilin University of Finance and Economics, 130117 Changchun, China · School of Engineering, Computer and Mathematical Sciences, Auckland University of Technology, Auckland, New Zealand
What Should an Agent Forget? Separating What Is Stored from What Is Used
Sep 9, 2026Yuhang Li, Yuchen LiPersistent Memory for Language Models Temporal IR
East China Normal University Shanghai, China
Closing the Consistency Gap: Self-Evolving Agents That Learn to Stay on Course
Sep 8, 2026Evelyn Duesterwald, Benjamin Elder, Lilian Ngweta +2LLM Agent Reliability Self-Evolving Agents
IBM Software Innovation Lab · IBM Research
MEMO: Multimodal Evidence Memory Organization for Long-Horizon LLM Agents
Sep 7, 2026Xian Gao, Jinpeng Wang, Jiacheng Ruan +3Multimodal Memory Long-Horizon LLM Agents
Shanghai Jiao Tong University · Tsinghua University · Institute of Automation of the Chinese Academy of Sciences
RuleMem: Active Rule Memory for Long-Term Conversational Agents
Sep 3, 2026Xingyuan Zeng, Zuohan Wu, Quanming Yao +5Question Answering Long-Term Conversational Memory
Sun Yat-sen University, Zhuhai, China · The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · Tsinghua University, State Key Laboratory of Space Network and Communications, Beijing National Research Center for Information Science and Technology, Beijing, China +2
Remember and Reweight: Enhancing Multi-Agent Debate with Experience Memory and Confidence Estimation
Sep 3, 2026Xuanfa Jin, Zhijian Ma, Yongcheng Zeng +3AI Agent Reliability Multi-Agent Debate
Institute of Automation, Chinese Academy of Sciences · University of Chinese Academy of Sciences · University College London
MemoryLACE: Memory Lifecycle-Aware Consolidation and Evidence Retrieval
Sep 2, 2026Meriem Yacoubi, Pia Schmidt, Nenad Petrovic +3Persistent Memory for Language Models Long-Term Conversational Memory
Chair of Robotics, Artificial Intelligence and Real-Time Systems, Technical University of Munich · inovex GmbH · Cerebras Systems Inc.
MemoryWalker: Stop Training Agents on Contexts They Never Saw
Sep 1, 2026Zinco J, Xunjie Zhu, Shen Huang +3Tool-Augmented Language Model Agents Consistency Distillation
Token Foundry, Alibaba Group
AgenticRag-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing
Aug 30, 2026Xinke Jiang, Yue Fang, Zhibang Yang +12Retrieval-Augmented Generation Agentic RAG
National Engineering Research Center of Software Engineering, Peking University, Beijing, China · School of Computer Science, Peking University, Beijing, China · Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China +3

Sep 27, 2026, cs.AIJ/K move · Enter open · S save

Self-Designed Evaluators and Warm Memory for Long-Horizon Agents

Saeid Asgari, Emre Kiciman, Leonardo de Oliveira Nunes, Ranveer Chandra

Microsoft

Language Model Generation Evaluation Long-Horizon Agent Evaluation Language Model Self-Assessment LLM Agent Self-Improvement AI Agent Benchmarks Memory-Augmented Language Model Agents

Open paper AskPDF arXiv

A tool-using language-model agent deployed over a long stream of tasks receives no reward, so it cannot tell whether it succeeded, cannot safely retry, and cannot label the experience it needs to improve. We present SelfSuite, in which the agent's own base model, given only the world's public materials, designs a small evaluation suite of weighted judges and grounded per-task briefs, freezes it, and uses it to gate a keep-best retry and to label a typed, outcome-tracked memory. On matched five-repeat benchmarks over tau2-bench and AppWorld, SelfSuite scores above the plain agent without any labels, matches methods given ten expert labels on tau2-bench, and trails Agentic Context Engineering (ACE) on AppWorld, where code execution gives a direct success signal. In an ablation campaign run on the same tasks, it is above label-free ACE in every repeat, and the gated second attempt is the only component whose removal hurts in every repeat. We also simulate a subject-matter expert who grades ten onboarding tasks per world. Using those labels to calibrate SelfSuite's evaluator gives a small, consistent gain, and using them to warm up ACE's memory lifts ACE to tie calibrated SelfSuite. A single-run study on a second model family shows the same ordering.

Momentum

Related topics

Latest papers 275