迈向个性化大语言模型驱动的代理：基础、评估与未来方向
Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions
AI总结：
本文探讨个性化LLM代理的基础、评估及未来方向，分析了四个核心能力：用户画像建模、记忆、规划与行动执行，并总结了评估指标和应用场景。
摘要：
大语言模型使能够推理、规划并与其他工具和环境交互的代理系统得以完成复杂任务。随着这些代理在长时间交互中运行，其效果越来越依赖于适应个体用户并保持交互连续性，从而产生个性化LLM驱动的代理（PLAs）。在长期、用户依赖的设置中，个性化渗透整个决策流程，而非仅限于表面响应生成。本文从能力角度回顾了个性化LLM代理。现有工作围绕四个相互依赖的能力：用户画像建模、记忆、规划和行动执行进行组织。通过这种分类法，代表性方法被综合分析，以说明用户信号如何在代理流程中表示、传播和利用，突出跨组件交互和重复出现的设计挑战。进一步探讨了针对个性化代理的评估指标和基准测试范式，以及从对话助手到领域专家系统的应用场景。通过明确代理系统中个性化的设计空间，本文为开发更用户导向、适应性强且可部署的LLM代理提供了结构化基础。
英文摘要：
Large language models have enabled agentic systems that reason, plan, and interact with tools and environments to accomplish complex tasks. As these agents operate over extended interaction horizons, their effectiveness increasingly depends on adapting behavior to individual users and maintaining continuity across interactions, giving rise to personalized LLM-powered agents (PLAs). In such long-term, user-dependent settings, personalization permeates the entire decision pipeline rather than remaining confined to surface-level response generation. This survey provides a capability-oriented review of personalized LLM-powered agents. Existing work is organized around four interdependent capabilities: profile modeling, memory, planning, and action execution. Using this taxonomy, representative methods are synthesized and analyzed to illustrate how user signals are represented, propagated, and utilized across the agent pipeline, highlighting cross-component interactions and recurring design challenges. Evaluation metrics and benchmarking paradigms tailored to personalized agents are further examined, along with application scenarios ranging from conversational assistants to domain-specific expert systems. By clarifying the design space of personalization in agent systems, this survey provides a structured foundation for developing more user-aligned, adaptive, and deployable LLM-powered agents.
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。
