LLM Agent Memory

LLM: Large Language Model

Overview

LLM agent memory studies how systems preserve useful facts, user preferences, task state, and reusable procedures beyond the current context window, so they can act consistently across sessions and long workflows. Common approaches include summarizing or retaining raw episodes, structured temporal or graph stores, retrieval-augmented memory, hierarchical episodic and procedural tiers, and learned policies for writing, consolidation, selection, and forgetting. Work is tested on long-horizon dialogue and personalization benchmarks such as LoCoMo and LongMemEval, as well as coding, web, tool-use, and embodied tasks; newer evaluations probe multi-turn learning, changing facts, and whether agents actually use retrieved evidence. The central tension is that compression and selective retrieval save tokens but can discard evidence or introduce stale, conflicting, biased, or poisoned memories, while larger stores and elaborate retrieval add cost and raise privacy and governance concerns.

Latest papers

CardsList

401 papers37 papers in the last four weeks, down 54% on the four weeks before. 0.3% of all new papers.

  1. OpenSage: Self-programming Agent Generation Engine

    Feb 18, 2026Hongwei Li, Zhun Wang, Qinrun Dai +11LLM Agent OrchestrationSelf-Evolving Agents

  2. MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks

    Feb 18, 2026Zexue He, Yu Wang, Churan Zhi +11Agent MemoryLLM Agent Memory

  3. Evaluating Memory Structure in LLM Agents

    Feb 11, 2026Alina Shutova, Alexandra Olenina, Ivan Vinogradov +1LLM Agent MemoryLLM Agent Evaluation

  4. Toward Efficient Agents: Memory, Tool learning, and Planning

    Jan 20, 2026Xiaofang Yang, Lijun Li, Heng Zhou +12LLM Agent MemoryAI Agent Benchmarks

  5. Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents

    Jan 12, 2026Miao Su, Yucan Guo, Zhongni Hou +8LLM Agent MemoryConversational Memory

  6. LLMs Can't Play Hangman: On the Necessity of a Private Working Memory for Language Agents

    Jan 11, 2026Davide Baldelli, Ali Parviz, Amal Zouaq +1LLM Agent MemoryLLM Agent Reliability

  7. Beyond Static Summarization: Proactive Memory Extraction for LLM Agents

    Jan 8, 2026Chengyuan Yang, Zequn Sun, Wei Wei +1Agent Memory ManagementPersistent Memory for Language Models

  8. CaveAgent: Transforming LLMs into Stateful Runtime Operators

    Jan 4, 2026Maohao Ran, Zhenglin Wan, Cooper Lin +21LLM Agent MemoryLLM Agents

  9. SEDM: Selective Self-Evolving Distributed Memory for Agents

    Sep 11, 2025Yichen Liu, Anna Min, Yinzhi Wang +14LLM Agent MemoryAgent Memory Management

  10. Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions

    Jul 7, 2025Yuanzhe Hu, Yu Wang, Julian McAuleyLLM Agent MemoryLLM Agent Evaluation