O-Mem：面向个性化、长周期、自演进智能体的全能记忆系统

摘要

近期基于大语言模型的智能体技术虽在生成类人应答方面展现出显著潜力，但在复杂环境中维持长期交互仍面临挑战，主要源于情境一致性与动态个性化能力的局限。现有记忆系统多依赖检索前的语义分组机制，易忽略语义无关却关键的用户信息，并引入检索噪声。本报告提出新型记忆框架O-Mem的初步设计，该框架基于主动用户画像，能动态提取并更新用户与智能体主动交互中产生的特征与事件记录。O-Mem支持人物属性与话题相关情境的分层检索，从而实现更具适应性与连贯性的个性化应答。在公开基准测试中，O-Mem在LoCoMo上达到51.67%的准确率，较此前最优模型LangMem提升近3%；在PERSONAMEM上获得62.99%的准确率，较前最优模型A-Mem提升3.5%。与现有记忆框架相比，O-Mem还显著提升了令牌处理效率与交互响应速度。本研究为未来开发高效类人的个性化AI助手开辟了新的方向。

English

Recent advancements in LLM-powered agents have demonstrated significant potential in generating human-like responses; however, they continue to face challenges in maintaining long-term interactions within complex environments, primarily due to limitations in contextual consistency and dynamic personalization. Existing memory systems often depend on semantic grouping prior to retrieval, which can overlook semantically irrelevant yet critical user information and introduce retrieval noise. In this report, we propose the initial design of O-Mem, a novel memory framework based on active user profiling that dynamically extracts and updates user characteristics and event records from their proactive interactions with agents. O-Mem supports hierarchical retrieval of persona attributes and topic-related context, enabling more adaptive and coherent personalized responses. O-Mem achieves 51.67% on the public LoCoMo benchmark, a nearly 3% improvement upon LangMem,the previous state-of-the-art, and it achieves 62.99% on PERSONAMEM, a 3.5% improvement upon A-Mem,the previous state-of-the-art. O-Mem also boosts token and interaction response time efficiency compared to previous memory frameworks. Our work opens up promising directions for developing efficient and human-like personalized AI assistants in the future.

O-Mem：面向个性化、长周期、自演进智能体的全能记忆系统

O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents

摘要

Support