ProPerSim: Developing Proactive and Personalized AI Assistants through User-Assistant Simulation

2025-09-25

AI Summary

Addressing the challenge of simultaneously achieving proactivity and personalization in AI assistants for real-world home environments, this paper proposes ProPerSim—a novel framework that systematically integrates both capabilities for the first time. Methodologically, it establishes a multi-role user-agent simulation environment powered by large language models (LLMs), augmented by retrieval-augmented generation (RAG), preference-aligned modeling, and an online feedback-driven continual learning mechanism to form a closed-loop optimization system. Key contributions include: (1) a persona-driven proactive triggering strategy, and (2) preference-aware dynamic policy adaptation. Extensive experiments across 32 diverse user personas demonstrate that ProPerAssistant significantly improves recommendation timeliness and preference alignment, with sustained growth in user satisfaction—validating the effectiveness and feasibility of synergistic proactive-personalized modeling.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

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.

Problem

• Developing proactive and personalized AI assistants for daily life
• Combining proactivity and personalization in home scenario simulations
• Creating assistants that learn from user feedback to improve satisfaction

Innovation

• Simulation framework for proactive personalized assistants
• Retrieval-augmented system learning from user feedback
• Adaptive strategy improving satisfaction across personas