https://doi.org/10.1051/epjconf/202532801021
Enhancing Personalized Fitness: Integrating Large Language Model
Shri Ramdeobaba College of Engineering and Management, Department of Computer Engineering, Nagpur 440013, India
* Corresponding author: abhashgoyal200@gmail.com
Published online: 18 June 2025
This paper explores the integration of Large Language Models (LLMs) into workout planning and personal training to meet the growing demand for personalized fitness solutions. Traditional personal training, while effective, faces challenges in accessibility, scalability, and real-time adaptability. We propose a novel AI-powered approach using LLMs to address these limitations and enhance the training experience. Our methodology combines the natural language processing capabilities of LLMs with exercise science and nutrition principles. The system provides 24/7 personalized guidance, dynamic workout adjustments, and data analysis from health sources. It understands user inputs, generates customized plans, and engages in natural, fitness-related dialogue. We assess effectiveness using user engagement metrics, fitness outcomes, and comparisons with conventional training. Results show improvements in accessibility, consistency, and personalization. The system adapts to individual needs and delivers evidence-based recommendations. This paper also examines the broader impact of AI in fitness, including public health potential, ethical considerations, and future development. By showcasing LLM integration in personal fitness, we contribute to the evolving landscape of health and wellness technologies and highlight its potential to transform how individuals approach fitness and preventive care.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
