拆分记忆、学习与个性化，让智能代理真正懂你。
MAPLE: A Sub-Agent Architecture for Memory, Learning, and Personalization in Agentic AI Systems
- 将记忆、学习、个性化拆分为三个独立子代理，各司其职。
- 个人化得分提升14.6%，特质采纳率从45%升至75%。
- 适合需要长期适应用户的复杂交互系统开发者。
大语言模型代理在处理复杂任务方面表现强劲，但其对个体用户的适应能力仍存在根本性局限。我们认为，这一问题源于架构上的混淆：当前系统将记忆、学习与个性化视为单一能力，而非三种需不同基础设施、不同时间尺度并可独立优化的机制。为此，我们提出MAPLE（Memory-Adaptive Personalized LEarning），通过原则性分解实现三者分离：记忆负责存储与检索基础设施；学习异步提取交互积累的知识；个性化则在有限上下文预算内实时应用学习成果。每个组件作为独立子代理，配备专用工具与明确接口。在MAPLE-Personas基准上的实验表明，该架构相较无状态基线，个人化得分提升14.6%（p < 0.01，Cohen's d = 0.95），特质采纳率从45%增至75%，显著增强代理的持续学习与适应能力。
原文摘要 · Abstract (English)
Large language model (LLM) agents have emerged as powerful tools for complex tasks, yet their ability to adapt to individual users remains fundamentally limited. We argue this limitation stems from a critical architectural conflation: current systems treat memory, learning, and personalization as a unified capability rather than three distinct mechanisms requiring different infrastructure, operating on different timescales, and benefiting from independent optimization. We propose MAPLE (Memory-Adaptive Personalized LEarning), a principled decomposition where Memory handles storage and retrieval infrastructure; Learning extracts intelligence from accumulated interactions asynchronously; and Personalization applies learned knowledge in real-time within finite context budgets. Each component operates as a dedicated sub-agent with specialized tooling and well-defined interfaces. Experimental evaluation on the MAPLE-Personas benchmark demonstrates that our decomposition achieves a 14.6% improvement in personalization score compared to a stateless baseline (p < 0.01, Cohen's d = 0.95) and increases trait incorporation rate from 45% to 75% -- enabling agents that genuinely learn and adapt.
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。