Abstract

Creating personalized, actionable exercise plans often requires iterative planning with experts, which can be costly and inaccessible to many individuals. This work explores the capabilities of LLM-driven conversational agents in addressing these challenges. Guided by our preliminary study with exercise planners and clients, we introduce PlanFitting, an LLM-driven conversational agent designed to assist users in creating and refining personalized weekly exercise plans. By engaging users in free-form conversations, PlanFitting helps elicit users’ goals, availabilities, and potential obstacles, and enables individuals to generate personalized exercise plans aligned with established exercise guidelines. Our study—involving a user study, intrinsic evaluation, and expert evaluation—demonstrated PlanFitting’s ability to guide users to create tailored, actionable, and evidence-based plans. We discuss future design opportunities for LLM-driven conversational agents to create plans that better comply with exercise principles and accommodate personal constraints.