Memory-Augmented Language Model Agents

Overview

This field studies how language-model agents can retain and reuse information beyond the current prompt, including user facts, task state, prior successes and failures, and procedural skills. Common approaches include retrieval from vector or graph stores, hierarchical summaries and context compression, and learned policies for deciding what to write, retrieve, update, or forget; some methods also encode experience into model parameters or latent representations. Evaluations span conversational recall benchmarks such as LoCoMo and LongMemEval, interactive settings such as ALFWorld and WebShop, and applications in coding, robotics, and clinical reasoning. A central tension is that memory can improve continuity and reduce context costs but also introduce stale or misleading information, negative transfer, privacy risks, and security vulnerabilities, so reliable lifecycle management and realistic long-horizon evaluation remain open challenges.

Latest papers

CardsList

472 papers43 papers in the last four weeks, down 46% on the four weeks before. 0.3% of all new papers.

  1. LMMR: Learned Multigranular Memory Retrieval for Small Language Model Agents

    Nov 17, 2026Pengfeng Song, Yunkai Zhuang, Liye ShiMulti-Hop RAGMemory-Augmented Language Model Agents

  2. MemDoctor: Stage-wise Error Attribution and Repair for MLLM Agent Memory

    Nov 16, 2026Ruiyang Jiang, Xinyang Liao, Weikai Huang +3LLM Agent MemoryMemory-Augmented Language Model Agents

  3. Experience Rot: Experienced Agents Fail Where Novices Succeed

    Nov 16, 2026Zhen Xu, Hang Yin, Zitao Zhang +2Experience Learning for LLM AgentsMemory-Augmented Language Model Agents

  4. Discovering Effective Agent Memory Designs through Program Evolution

    Nov 12, 2026Xinheng Ding, Seyyed Saeid Cheshmi, Ziyang Zhang +5Agent MemoryMemory Management for LLM Agents

  5. Controlled Knowledge Engineering for Taxonomy Induction with Tool-Grounded LLM Agents and Runtime-Adaptive Policies

    Nov 10, 2026Jonas Limniatis, Bennet Schaarmann, Georg Reuber +1Taxonomy InductionLLM Agents

  6. TreeAgent: Structure-Aware Memory Agent for Processing Long Hierarchical Data

    Nov 10, 2026Wei Gu, Weiwei Qi, Jiajun Tang +5structured memory for llm agentsMemory-Augmented Language Model Agents

  7. BioMem: Agentic Memory for Biomedical LLM Agents

    Nov 10, 2026Mingchen Li, Yongkang Xiao, Rumeng Li +2Memory-Augmented Language Model AgentsMemory Management for LLM Agents

  8. MIRIX-2.0: Multi-Agent Memory System

    Nov 9, 2026Wei-Chieh Huang, Weizhi Zhang, Jiayan Nan +2Agent MemoryAgent Memory Management

  9. Think or Remember: The Exchange Rate of Agentic Inference

    Nov 7, 2026Juan Wisznia, Santiago Luis Groba Alonso, Matías Gómez Taddeo +3Cost-Aware InferenceEfficient Language Model Inference

  10. Remembering Is Not Enough: Evaluating Timing and Omission in Longitudinal AI Mental Health Support

    Nov 5, 2026Eli Min, Mohit Chandra, Aamogh Sawant +8Mental Health Conversational AgentsMulti-Turn Language Model Safety Evaluation

  11. The Memory Trap: Language Agents Overgeneralize from Benign Interactions

    Nov 5, 2026Kaiqu Liang, Jaime Fernández Fisac, Thomas L. Griffiths +1Memory-Augmented Language Model AgentsLLM Agent Safety

  12. Graph-Mediated Large Language Model Systems in the Agentic Era: Reasoning, Knowledge, Retrieval, Execution, and Coordination

    Nov 4, 2026Haihui Liu, Yang Chen, Zice Qiu +5LLM Reasoning with GraphsGraph-Based Agent Memory

  13. HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation

    Nov 3, 2026Zhen Tao, Xun Zhou, Xuhui Chen +2Recommender SystemsLarge Language Model-Based Recommendation

  14. El Agente Fármaco: A Scalable AI Scientist for Drug Discovery

    Nov 2, 2026Marcel Müller, Mohammad Ghazi Vakili, Yoshihiro Ogura +13Drug DiscoveryScientific Workflow Automation

  15. Multi-Modal Multi-Agent System for Bridge Operation and Maintenance based on Large Language Model

    Nov 2, 2026Xiangyun Luo, Yunkai Zhang, Yong Huang +2Multi-Agent LLM SystemsMultimodal Agents

  16. MemRole: From Memories to Decisions for Long-Horizon Reasoning in Role-Playing Agents

    Nov 1, 2026Mengting Li, Xilong Cheng, Zhihao Xiao +6Large Language Model-Based Role-Play SimulationMemory-Augmented Language Model Agents

  17. Pulse: Long-Horizon Tasks Need Streaming Personalization

    Oct 31, 2026Qijia Zhuang, Jialiang Liang, Yuxiang RenLong-Horizon LLM AgentsMemory-Augmented Language Model Agents

  18. KEEPER: Learning Control-Sufficient Textual Memory for Long-Horizon LLM Agents

    Oct 30, 2026Jinkyeong Choi, Chaebin Jeong, Junsung Jeon +1LLM Agent MemoryMemory-Augmented Language Model Agents

  19. When to Assist and What to Suggest: Joint Gating and Memory-Grounded Hint Generation in One Compact Decoder

    Oct 29, 2026A. J. A. Jubayer Talukder, Mohammad Ariful HaqueConversational AgentsMemory-Augmented Language Model Agents

  20. HERA: Assessing an Autonomous Agent for Quantum Device Measurement

    Oct 29, 2026Zachary W. Gomez, Nathan Bittner, Jordan T. McCourt +7Autonomous ExperimentationAutonomous Research Agents

  21. Routed Continual Learning

    Oct 28, 2026Michael Philip, Mahesh Balakrishnan, David Geraghty +3Continual Learning for LLM AgentsMemory-Augmented Language Model Agents

  22. SkillMem: Compact External Skill Memory for Latent Multi-Agent Reasoning

    Oct 27, 2026Yuxuan Zhu, Mohammad Mohammadi Amiri, Pin-Yu Chen +1Procedural Memory for LLM AgentsMemory-Augmented Language Model Agents

  23. From Voiceprints to User Entities: Online Speaker-Memory Construction for Multi-User Spoken Agents

    Oct 27, 2026Yucong Zhang, Cancan Li, Bo Xiao +2Conversational MemoryMemory-Augmented Language Model Agents

  24. AutoEnergyDesign: An LLM-Driven Agent for Automatic Energy System Design Optimization

    Oct 26, 2026Amedeo Buonanno, Salvatore Fabozzi, Maria ValentiLarge Language Model-Guided OptimizationMemory-Augmented Language Model Agents

  25. CaliMem: Search-Efficient Data Agent via Calibrated Memory

    Oct 25, 2026Hanze Li, Athan Z. Li, Feiyang Kang +4Training Data CurationMemory-Augmented Agents