"Having Lunch Now": Understanding How Users Engage with a Proactive Agent for Daily Planning and Self-Reflection

2025-09-28

AI Summary

This study investigates how proactive conversational agents—designed as coaching partners rather than passive tools—can support users’ daily planning and self-reflection to foster sustainable behavior change. Using a longitudinal user experience research approach, we deployed a dialogue system featuring periodic proactive check-ins over 14 days, collecting and analyzing interaction logs and qualitative feedback. Three key phenomena emerged: (1) the dynamic co-construction of shared mental models between user and agent; (2) user resistance and adaptive negotiation during recommendation delivery; and (3) negative impacts on engagement stemming from agent rigidity—e.g., premature handoffs or overcommitment. Based on these findings, we propose design principles for behavior-change agents emphasizing flexibility, collaborative negotiation, and incremental trust building. The study provides empirical grounding and novel design insights for conversational AI in health promotion and habit formation.

Technology Category

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

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Conversational agents have been studied as tools to scaffold planning and self-reflection for productivity and well-being. While prior work has demonstrated positive outcomes, we still lack a clear understanding of what drives these results and how users behave and communicate with agents that act as coaches rather than assistants. Such understanding is critical for designing interactions in which agents foster meaningful behavioral change. We conducted a 14-day longitudinal study with 12 participants using a proactive agent that initiated regular check-ins to support daily planning and reflection. Our findings reveal diverse interaction patterns: participants accepted or negotiated suggestions, developed shared mental models, reported progress, and at times resisted or disengaged. We also identified problematic aspects of the agent's behavior, including rigidity, premature turn-taking, and overpromising. Our work contributes to understanding how people interact with a proactive, coach-like agent and offers design considerations for facilitating effective behavioral change.

Problem

• Understanding user engagement with proactive conversational agents
• Identifying interaction patterns in daily planning and reflection
• Addressing problematic behaviors in coach-like agent interactions

Innovation

• Proactive agent initiates regular check-ins
• Agent supports daily planning and reflection
• Identifies interaction patterns and problematic behaviors