EvoHIIT: LLM-Assisted Evolutionary Design of High Intensity Interval Training programs

Introduction EvoHIIT is built on top of the LLaMEA framework, repurposed to generate and evaluate HIIT programs. LLaMEA (Large Language Model Evolutionary Algorithm) is an innovative framework that leverages the power of large language models (LLMs), such as GPT-4, for the automated generation and refinement of metaheuristic optimization algorithms. The framework utilizes a novel approach to evolve and optimize algorithms iteratively based on performance metrics and runtime evaluations without requiring extensive prior algorithmic knowledge. This makes LLaMEA an ideal tool for both research and practical applications in fields where optimization is crucial. Installation Important The Python version must be 3.11 or higher.You need an OpenAI, Gemini, or Ollama API key to use LLM models. You can install the package from source using uv (version 0.7.19).Make sure you have uv installed. Download and unpack this repository. Install the required dependencies via uv: uv sync Quick Start 1. Set up an OpenAI API key Obtain an API key from OpenAI. Set the API key in your environment variables: export OPENAI_API_KEY='your_api_key_here' 2. Running an Experiment The EvoHIIT experiments are located in the HIIT_maker folder. 3. Viewing Results Results of the experiments are stored in the results folder.They can be visualized using the scripts from the HIIT_maker folder.