Me-Agent：一种具有两级用户习惯学习的个性化移动代理以增强交互
Me-Agent: A Personalized Mobile Agent with Two-Level User Habit Learning for Enhanced Interaction
AI总结：
Me-Agent通过两级用户习惯学习方法，提升移动代理在个性化交互中的性能与准确性。
摘要：
基于大型语言模型（LLM）的移动代理在性能上取得了显著进步。然而，这些代理往往遵循显式用户指令而忽视个性化需求，导致对真实用户来说存在重大局限，尤其是在没有个性化上下文的情况下：（1）无法解释模糊的指令，（2）缺乏从用户交互历史中学习的能力，（3）无法处理个性化指令。为缓解上述挑战，我们提出了Me-Agent，一种可学习且可记忆的个性化移动代理。具体而言，Me-Agent采用了一种两级用户习惯学习方法。在提示层面，我们设计了一种增强个人奖励模型的用户偏好学习策略，以提高个性化性能。在记忆层面，我们设计了一种分层偏好记忆，它在不同级别的记忆中存储用户的长期记忆和应用特定的记忆。为了验证移动代理的个性化能力，我们引入了User FingerTip，一个新的基准，包含大量日常生活的模糊指令。在User FingerTip和通用基准上的广泛实验表明，Me-Agent在个性化方面实现了最先进的性能，同时保持了竞争性的指令执行性能。
英文摘要：
Large Language Model (LLM)-based mobile agents have made significant performance advancements. However, these agents often follow explicit user instructions while overlooking personalized needs, leading to significant limitations for real users, particularly without personalized context: (1) inability to interpret ambiguous instructions, (2) lack of learning from user interaction history, and (3) failure to handle personalized instructions. To alleviate the above challenges, we propose Me-Agent, a learnable and memorable personalized mobile agent. Specifically, Me-Agent incorporates a two-level user habit learning approach. At the prompt level, we design a user preference learning strategy enhanced with a Personal Reward Model to improve personalization performance. At the memory level, we design a Hierarchical Preference Memory, which stores users' long-term memory and app-specific memory in different level memory. To validate the personalization capabilities of mobile agents, we introduce User FingerTip, a new benchmark featuring numerous ambiguous instructions for daily life. Extensive experiments on User FingerTip and general benchmarks demonstrate that Me-Agent achieves state-of-the-art performance in personalization while maintaining competitive instruction execution performance.
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。
