cs.AINov 9, 2026

Can LLM Agents Organize Their Own Memory?

Authors: Zichuan Fu, Junjia Qi, Wenlin Zhang, Yimin Deng, Shirong Wang, Jinyang Li, Xian Wu, Xiangyu Zhao

Organizations: City University of Hong Kong · Tencent Jarvis Lab

Abstract

In most LLM agents, weights are fixed after deployment, so new information must be retained in external memory. Existing approaches often rely on predefined records and fixed organizational rules, which cannot readily accommodate evolving tasks and interactions. This raises the question: can LLM agents organize their own memory using ordinary documents? We introduce self-organized memory (SoMem), a framework that stores memory in linked documents. The agent decides what to summarize, how to group related information, and when to revise existing topics, and every summary it produces stays linked to the original interactions as evidence. The runtime validates updates and automatically derives temporal, relational, and recent-memory views from the organized content. At query time, the agent chooses what to search and read, following document links and inspecting original evidence as needed. On LoCoMo, BEAM-100K, and LongMemEval-S, SoMem outperforms the strongest baseline by 2.66, 3.10, and 2.00 percentage points, respectively. The constructed memory can be reused across models, and additional reasoning effort can further improve answer quality. These findings demonstrate the feasibility of agents organizing and using their own persistent memory through ordinary documents. Code is available at: https://github.com/Qi202/SoMem.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability

    Jul 29, 2026Sizhe Zhou, Sheldon Yu, Hui Wei +8Agent MemoryLLM Agent Memory

  2. Mem++: Non-Destructive Memory for Long-Term Organizational LLM Agents

    Oct 1, 2026Ahmad Yehia, Aly O. Abdelkareem, Islam Ahmed +4LLM Agent MemoryPersistent Memory for Language Models

  3. EdgeMem: LLM-Free Agent Memory Construction and Retrieval via Evidence-Preserving Multi-Anchor Hypergraph

    Sep 3, 2026Zeyang Cui, Jiannong Cao, Zhiyuan Wen +3Agent MemoryMemory Management for LLM Agents