不重训模型也能让智能体自我进化，靠的是记忆系统升级。
Beyond Training: Enabling Self-Evolution of Agents with MOBIMEM
- 用三种专用记忆模块解耦进化与模型权重，避免反复训练。
- 用户画像匹配准确率达83.1%，检索速度比基线快280倍。
- 适合移动设备上需要持续优化的智能体应用，如手机自动化。
大型语言模型（LLM）代理正被广泛部署于移动端和桌面端以自动化复杂流程。然而，现有以模型为中心的代理架构在部署后难以实现自我演化：提升个性化、能力与效率通常需持续重训练或微调，带来高昂计算开销，并存在模型精度与推理效率的固有权衡。为在无需模型重训练的前提下实现迭代自演化，我们提出MOBIMEM——一种以记忆为核心的代理系统。MOBIMEM引入三种专用记忆原语，将代理演化从模型权重中解耦：(1) 配置记忆采用轻量级距离图（DisGraph）结构，实现用户偏好对齐，解决用户画像检索中的精度-延迟权衡；(2) 经验记忆使用多层级模板实例化新任务执行逻辑，保障能力泛化；(3) 行动记忆记录细粒度交互序列，降低对昂贵模型推理的依赖。在此记忆架构基础上，MOBIMEM进一步集成一系列操作系统式服务以协调执行：调度器负责并行子任务与内存操作；代理记录-回放（AgentRR）机制实现安全高效的行动复用；上下文感知异常处理确保在用户中断或运行时错误下优雅恢复。在AndroidWorld及前50名应用上的评估显示，MOBIMEM实现了83.1%的配置对齐率，画像检索时间仅23.83毫秒（比GraphRAG基线快280倍），任务成功率最高提升50.3%，端到端延迟最高降低9倍。
原文摘要 · Abstract (English)
Large Language Model (LLM) agents are increasingly deployed to automate complex workflows in mobile and desktop environments. However, current model-centric agent architectures struggle to self-evolve post-deployment: improving personalization, capability, and efficiency typically requires continuous model retraining/fine-tuning, which incurs prohibitive computational overheads and suffers from an inherent trade-off between model accuracy and inference efficiency. To enable iterative self-evolution without model retraining, we propose MOBIMEM, a memory-centric agent system. MOBIMEM first introduces three specialized memory primitives to decouple agent evolution from model weights: (1) Profile Memory uses a lightweight distance-graph (DisGraph) structure to align with user preferences, resolving the accuracy-latency trade-off in user profile retrieval; (2) Experience Memory employs multi-level templates to instantiate execution logic for new tasks, ensuring capability generalization; and (3) Action Memory records fine-grained interaction sequences, reducing the reliance on expensive model inference. Building upon this memory architecture, MOBIMEM further integrates a suite of OS-inspired services to orchestrate execution: a scheduler that coordinates parallel sub-task execution and memory operations; an agent record-and-replay (AgentRR) mechanism that enables safe and efficient action reuse; and a context-aware exception handling that ensures graceful recovery from user interruptions and runtime errors. Evaluation on AndroidWorld and top-50 apps shows that MOBIMEM achieves 83.1% profile alignment with 23.83 ms retrieval time (280x faster than GraphRAG baselines), improves task success rates by up to 50.3%, and reduces end-to-end latency by up to 9x on mobile devices.
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。