发表机构
Noah’s Ark Lab, Huawei Technologies（华为技术有限公司诺亚方舟实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出MindMemOS内存操作层，通过多种算法实现内存自适应建模与技能演进，在多个数据集上取得显著性能提升。
AI 中文摘要
内存是AI智能体的核心组件，使其能积累经验、维持个性化并在长期交互中适应。然而，现有内存系统在开发后往往保持固定，限制了其通过持续使用调整内存模型、组织策略和过程知识的能力。我们提出MindMemOS，一种可移植且自演进的内存操作层，通过统一的实体属性时间结构组织开放世界信息。MindMemOS支持场景自适应内存建模、高阶模式发现、自主内存优化及持续技能演进。其MindMemEvolve算法采用验证驱动的进化搜索，为目标场景优化内存模式；而dreaming功能通过合并冗余记录和解决冲突来整合积累的内存。此外，隐式纠正反馈作为人在回路信号，用于识别和修正潜在不准确或不一致的内存。其MindSkillEvolve算法进一步将智能体执行轨迹转化为可复用且逐步优化的技能。MindMemOS在LOCOMO数据集上准确率达94.03%，在PersonaMem数据集上达70.63%；MindSkillEvolve使SpreadsheetBench任务成功率较初始技能基线提升9.2个百分点。
英文摘要
Memory is a core component of AI agents, enabling them to accumulate experience, maintain personalization, and adapt over long-term interactions. However, existing memory systems often remain fixed after development, limiting their ability to adapt their memory models, organization strategies, and procedural knowledge through continued use. We present MindMemOS, a portable and self-evolving memory operating layer that organizes open-world information using a unified entity property timestructure. MindMemOS supports scenario-adaptive memory modeling, higher-order pattern discovery, autonomous memory refinement, and continuous skill evolution. Its MindMemEvolve algorithm employs validation-driven evolutionary search to optimize memory schemas for target scenarios, whiledreaming consolidates accumulated memories by merging redundant records and resolving conflicts. In addition, implicit corrective feedback serves as a human-in-the-loop signal for identifying and revising potentially inaccurate or misaligned memories. Its MindSkillEvolve algorithm further transforms agent execution trajectories into reusable and progressively refined skills. MindMemOS achieves 94.03% accuracy on LOCOMO and 70.63% on PersonaMem. MindSkillEvolve improves SpreadsheetBench success by 9.2 percentage points over the initial-skill baseline.
Comments35 pages,14 figures
