PlanFitting: Personalized Exercise Planning with Large Language Model-driven Conversational Agent

TL;DR

PlanFitting leverages Large Language Models to create a conversational agent that helps users develop personalized, evidence-based exercise plans through interactive dialogue, reducing reliance on expert input.

Contribution

This work introduces PlanFitting, a novel LLM-driven conversational agent for personalized exercise planning, enabling user engagement and plan customization without expert intervention.

Findings

Successfully guided users to create tailored exercise plans

Demonstrated effectiveness through user, intrinsic, and expert evaluations

Showed potential for LLMs to assist in health-related planning tasks

Abstract

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.