arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.13258cs.AIcs.CLcs.MA
收藏

MAPLE:一种用于代理AI系统中记忆、学习和个性化的核心架构

MAPLE: A Sub-Agent Architecture for Memory, Learning, and Personalization in Agentic AI Systems

Deepak Babu Piskala

AI总结:

MAPLE通过分解记忆、学习和个性化为独立子代理,提升代理AI系统的个性化能力,实验显示在个性化得分和特征纳入率上有显著提升。

摘要:

大型语言模型(LLM)代理已经 emerged 作为复杂任务的强大工具,但它们适应个体用户的能力仍然从根本上受到限制。我们主张这种限制源于一个关键的架构混淆:当前系统将记忆、学习和个性化视为统一能力,而不是需要不同基础设施、不同时间尺度和需要独立优化的三个独立机制。我们提出了MAPLE(Memory-Adaptive Personalized LEarning),一种原则性的分解,其中记忆处理存储和检索基础设施;学习从积累的交互中异步提取智能;个性化在有限上下文预算内实时应用所学知识。每个组件都作为专门的子代理运行,具有专门的工具和明确的接口。在MAPLE-Personas基准上的实验评估表明,我们的分解在与无状态基线相比时,个性化得分提高了14.6%(p < 0.01,Cohen's d = 0.95),并使特征纳入率从45%提高到75%——使代理真正学会并适应。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑