用原子事实构建稳定长效记忆，让大模型记住用户长期信息。
AtomMem: Building Simple and Effective Memory System for LLM Agents via Atomic Facts
- 从对话中提取高价值原子事实，作为高效记忆单元
- 通过事件层级和时间轨迹追踪用户动态，支持跨会话记忆
- 适合需要个性化长期交互的智能代理系统
大型语言模型虽具强大推理与生成能力，但固定上下文窗口限制了其在多会话交互中长期信息的积累与复用。现有记忆增强系统常以粗粒度、不稳定的模式构建记忆，依赖低效表示或无约束更新。为此，我们提出AtomMem，一种面向高密度信息存储与稳定演化的长期记忆系统。AtomMem引入事实执行器，从长文本交互中选择性提取高价值原子事实，作为高效记忆表征。随后，系统将这些事实组织为层次化事件结构与时间轮廓，捕捉连贯的情景上下文并追踪用户属性的动态演变。检索时，系统激活关联记忆图以连接碎片化记忆。在LoCoMo基准上的实验表明，AtomMem在多种推理任务中达到当前最优性能，为部署智能个性化代理提供可扩展且经济可行的解决方案。
原文摘要 · Abstract (English)
Large language models (LLMs) demonstrate strong reasoning and generation abilities, but their fixed context windows limit long-term information accumulation and reuse across multi-session interactions. Existing memory-augmented systems often construct memory in a coarse and unstable manner, relying on inefficient memory representations or unstable unconstrained updates. To address these challenges, we propose AtomMem, a long-term memory system designed for value-dense storage and stable memory evolution. AtomMem introduces a Fact Executor, which selectively extracts high value atomic facts from long form interactions to serve as highly efficient memory representations. Subsequently, AtomMem organizes these facts into hierarchical event structures and temporal profiles, capturing coherent episodic contexts and tracking dynamically evolving user attributes over time. During retrieval, the system activates an associative memory graph to connect fragmented memories. Experiments on the LoCoMo benchmark confirm that AtomMem achieves state-of-the-art performance across various reasoning tasks, offering a scalable and economically viable solution for deploying intelligent personalized agents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。