Search papers, labs, and topics across Lattice.
This paper introduces FitOne, a series of domain-specific Large Language Models (LLMs) tailored for Scientific Fitness Coaching (SFC), addressing the limitations of general-purpose LLMs in this domain. By employing a three-stage post-training pipeline that includes continual pre-training, supervised fine-tuning, and reinforcement learning, FitOne demonstrates significant improvements in performance on professional fitness certification exams. The results indicate that FitOne-8B and FitOne-32B achieve average score increases of up to 10.09% and 9.29% on the ACSM-EP exam, respectively, while maintaining strong general capabilities.
FitOne outperforms general-purpose LLMs by up to 10% on fitness certification exams, showcasing the power of domain-specific training in AI applications.
Scientific Fitness Coaching (SFC) is typically delivered by human professionals, making it costly and inaccessible to many. While recent advances in Large Language Models (LLMs) show considerable promise for more inclusive fitness coaching, directly deploying prevailing general-purpose LLMs in SFC reveals critical limitations. These models often lack sufficient domain-specific knowledge integration, leading to weak performance on complex SFC scenarios. In this paper, we introduce FitOne, a series of fitness LLMs (with 8B and 32B parameters) designed to improve reliability and domain specialization for SFC applications. Built upon the Qwen3 foundation models, FitOne is developed through a three-stage post-training pipeline consisting of continual pre-training, supervised fine-tuning, and reinforcement learning, using large-scale, high-quality datasets derived from rigorous knowledge engineering. We conduct comprehensive evaluations of FitOne on professional fitness certification exams, including ACSM-EP and NSCA-CSCS, as well as general capabilities such as knowledge reasoning and instruction following. Experimental results show that, while retaining strong general capabilities, FitOne-8B/32B achieves average improvements of up to 10.09%/9.29% and 12.73%/7.01% on the ACSM-EP and NSCA-CSCS exams, respectively, compared with the Qwen3 base models. Furthermore, in-depth ablation studies confirm the necessity of each training stage, highlighting the pipeline's effectiveness in balancing domain expertise enhancement with general ability retention. We believe this research advances LLM systems toward more reliable fitness intelligence and will inspire future research on developing domain-specific LLMs.
