为个人AI设计可审计的记忆框架，支持跨设备持续服务。
Mi-Memory: A Lifecycle Memory Framework for Personal AI
- 分四角色管理记忆生命周期：结构、扩展、演化与部署。
- 在多个评测中表现优异，如LoCoMo任务达93.59%准确率。
- 适合关注隐私、延迟和多设备协同的AI系统开发者。
个人AI正从单向对话转向跨越手机、汽车、家居、可穿戴设备、摄像头和工具的持续服务。在此场景下，记忆不能仅作为历史对话缓存，而应成为连续性与治理基础：持久保存用户状态，基于多模态和设备证据生成回答，支持修正与遗忘，约束策略演进，并在延迟、成本、隐私及边缘-云部署限制下保持可用。本文提出Mi-Memory，一种围绕四个角色构建的个人AI生命周期记忆框架：结构、扩展、演化与部署。通过共享审计契约连接各角色，形成四类核心产物：带类型标记的证据载荷保留来源身份与溯源信息，诊断日志定位服务链路中的证据丢失，策略产物显式记录记忆策略变更，门控/回滚记录界定已接受的演化路径。Mi-Memory通过MemStack、MemSense/MemFuse、D$^{2}$ACCI/E$^{2}$MEND和LiteMem实现各角色功能。在受控基准的结构评估中，MemStack在LoCoMo、PersonaMem-V2和LongMemEval上分别达到93.59%、57.24%和87.47%的准确率；其他评测提供模块级、初步或内部验证、迁移可行性或仅设计层面证据并明确边界。MiMemory是迈向可审计、证据管控、部署感知的记忆系统的重要一步。项目主页：https://darwin-agent.github.io/Mi-Memory/
原文摘要 · Abstract (English)
Personal AI is moving beyond chat-only interaction toward continuous services that span phones, cars, homes, wearables, cameras, and tools. In this setting, memory cannot remain a cache of prior conversations. It should serve as a continuity and governance substrate: preserving durable user state, grounding answers in multimodal and device evidence, supporting correction and forgetting, bounding policy evolution, and remaining deployable under latency, cost, privacy, and edge-cloud constraints. This technical report presents Mi-Memory, a lifecycle memory framework for Personal AI organized around four roles: Structure, Expansion, Evolution, and Deployment. A shared audit contract links these roles through four recurring artifact families: typed evidence payloads preserve source identity and provenance, diagnostic traces localize evidence loss across the serving pipeline, strategy artifacts make memory-policy changes explicit, and gate/rollback records bound accepted evolution. MiMemory instantiates the roles through MemStack, MemSense/MemFuse, D$^{2}$ACCI/E$^{2}$MEND, and LiteMem. In controlled-reference Structure evaluations, MemStack reaches 93.59%, 57.24%, and 87.47% on LoCoMo, PersonaMem-V2, and LongMemEval, respectively; other tracks report module-level, preliminary/internal, transfer-feasibility, or design-only evidence with explicit boundaries. MiMemory is a step toward auditable, evidence-gated, and deployment-aware memory systems for Personal AI. Project homepage: https://darwin-agent.github.io/Mi-Memory/ .
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。