PersonaAgent：弥合个性化LLM智能体的记忆与行动
PersonaAgent: Bridging Memory and Action for Personalized LLM Agents
AI总结：
提出PersonaAgent框架，通过整合个性化记忆模块（情景与语义记忆）和行动模块，并利用角色提示作为中介实现记忆与行动的协同，以解决LLM智能体的个性化任务。
摘要：
由大型语言模型驱动的智能体近期作为先进范式出现，在广泛领域和任务中展现出令人印象深刻的能力。尽管潜力巨大，当前LLM智能体常采用一刀切方法，缺乏响应用户不同需求和偏好的灵活性。这一局限促使我们开发PersonaAgent——首个旨在处理多样化个性化任务的个性化LLM智能体框架。具体而言，PersonaAgent整合了两个互补组件：一个包含情景记忆和语义记忆机制的个性化记忆模块；一个使智能体能够执行针对用户定制的工具行动的个性化行动模块。核心在于，角色（定义为每位用户独特的系统提示）充当中间件：它利用来自个性化记忆的洞察来控制智能体行动，而这些行动的结果反过来又优化记忆。基于该框架，我们提出一种测试时用户偏好对齐策略，该策略模拟最近的n次交互以优化角色提示，通过模拟响应与真实响应之间的文本损失反馈确保实时用户偏好对齐。实验评估表明，PersonaAgent不仅有效个性化行动空间，还能在测试时实际应用中扩展，显著优于其他基线方法。这些结果证明了我们的方法在提供定制化、动态用户体验方面的可行性和潜力。
英文摘要：
Large Language Model (LLM) empowered agents have recently emerged as advanced paradigms that exhibit impressive capabilities in a wide range of domains and tasks. Despite their potential, current LLM agents often adopt a one-size-fits-all approach, lacking the flexibility to respond to users' varying needs and preferences. This limitation motivates us to develop PersonaAgent, the first personalized LLM agent framework designed to address versatile personalization tasks. Specifically, PersonaAgent integrates two complementary components - a personalized memory module that includes episodic and semantic memory mechanisms; a personalized action module that enables the agent to perform tool actions tailored to the user. At the core, the persona (defined as unique system prompt for each user) functions as an intermediary: it leverages insights from personalized memory to control agent actions, while the outcomes of these actions in turn refine the memory. Based on the framework, we propose a test-time user-preference alignment strategy that simulate the latest n interactions to optimize the persona prompt, ensuring real-time user preference alignment through textual loss feedback between simulated and ground-truth responses. Experimental evaluations demonstrate that PersonaAgent significantly outperforms other baseline methods by not only personalizing the action space effectively but also scaling during test-time real-world applications. These results underscore the feasibility and potential of our approach in delivering tailored, dynamic user experiences.
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。
