As large language models (LLMs) become increasingly integrated into daily life, there is growing demand for AI assistants that are not only reactive but also proactive and personalized. While recent advances have pushed forward proactivity and personalization individually, their combination remains underexplored. To bridge this gap, we introduce ProPerSim, a new task and simulation framework for developing assistants capable of making timely, personalized recommendations in realistic home scenarios. In our simulation environment, a user agent with a rich persona interacts with the assistant, providing ratings on how well each suggestion aligns with its preferences and context. The assistant's goal is to use these ratings to learn and adapt to achieve higher scores over time. Built on ProPerSim, we propose ProPerAssistant, a retrieval-augmented, preference-aligned assistant that continually learns and adapts through user feedback. Experiments across 32 diverse personas show that ProPerAssistant adapts its strategy and steadily improves user satisfaction, highlighting the promise of uniting proactivity and personalization.

翻译：随着大语言模型日益融入日常生活，对人工智能助手的需求不仅限于被动响应，更要求其具备主动性与个性化。尽管近期研究在主动性和个性化方面各自取得了进展，但二者的结合仍待深入探索。为填补这一空白，我们提出了ProPerSim——一个用于开发能够在真实家庭场景中提供及时、个性化推荐助手的新任务与仿真框架。在我们的仿真环境中，具有丰富人设的用户代理与助手进行交互，并根据每次建议与其偏好及情境的匹配程度提供评分。助手的目标是利用这些评分持续学习与适应，以随时间推移获得更高评分。基于ProPerSim，我们提出了ProPerAssistant——一个通过检索增强且偏好对齐的助手，能够借助用户反馈持续学习与适应。在32种不同人设上的实验表明，ProPerAssistant能够调整其策略并稳步提升用户满意度，这彰显了融合主动性与个性化技术的巨大潜力。