PlanFitting: Personalized Exercise Planning with Large Language Model-driven Conversational Agent
This addresses the issue of costly and inaccessible expert iteration for personalized exercise planning, though it appears incremental as an application of existing LLM technology to a specific domain.
The researchers tackled the problem of creating personalized exercise plans by developing PlanFitting, an LLM-driven conversational agent that assists users in generating tailored weekly plans through free-form conversations, and demonstrated its ability to produce actionable and evidence-based plans in a user study.
Creating personalized and actionable exercise plans often requires iteration with experts, which can be costly and inaccessible to many individuals. This work explores the capabilities of Large Language Models (LLMs) in addressing these challenges. We present PlanFitting, an LLM-driven conversational agent that assists 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.