让大模型像人一样长期记忆并自我整理信息，实现持续推理。
EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning
- 模仿大脑记忆机制，将对话转为可组织的内存单元
- 在LoCoMo和LongMemEval上表现超越现有方法
- 适合需要长期交互与用户画像的智能助手场景
大型语言模型（LLMs）正越来越多地作为长期交互代理部署，但其有限的上下文窗口使得在长时间互动中维持连贯行为变得困难。现有的记忆系统通常存储孤立记录并检索片段，难以整合动态演变的用户状态或解决冲突。我们提出EverMemOS，一种自组织的记忆操作系统，借鉴记忆痕迹（engram）生命周期设计计算记忆。情景轨迹生成将对话流转化为捕捉情景痕迹、原子事实和时间受限的前瞻信号的MemCells。语义巩固将MemCells组织为主题性MemScenes，提炼出稳定的语义结构并更新用户画像。重构回忆基于MemScene引导的代理检索，为下游推理生成必要且充分的上下文。在LoCoMo和LongMemEval上的实验表明，EverMemOS在记忆增强推理任务上达到最先进性能。我们还对PersonaMem v2进行了画像研究，并通过定性案例展示了其在聊天场景中的用户画像与前瞻能力。代码已公开于https://github.com/EverMind-AI/EverMemOS。
原文摘要 · Abstract (English)
Large Language Models (LLMs) are increasingly deployed as long-term interactive agents, yet their limited context windows make it difficult to sustain coherent behavior over extended interactions. Existing memory systems often store isolated records and retrieve fragments, limiting their ability to consolidate evolving user states and resolve conflicts. We introduce EverMemOS, a self-organizing memory operating system that implements an engram-inspired lifecycle for computational memory. Episodic Trace Formation converts dialogue streams into MemCells that capture episodic traces, atomic facts, and time-bounded Foresight signals. Semantic Consolidation organizes MemCells into thematic MemScenes, distilling stable semantic structures and updating user profiles. Reconstructive Recollection performs MemScene-guided agentic retrieval to compose the necessary and sufficient context for downstream reasoning. Experiments on LoCoMo and LongMemEval show that EverMemOS achieves state-of-the-art performance on memory-augmented reasoning tasks. We further report a profile study on PersonaMem v2 and qualitative case studies illustrating chat-oriented capabilities such as user profiling and Foresight. Code is available at https://github.com/EverMind-AI/EverMemOS.
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。