cornell-zhang/heurigym

This project helps evaluate how effectively large language models (LLMs) can create and improve heuristics to solve complex real-world optimization challenges. It takes various combinatorial optimization problems, such as airline crew pairing or protein sequence design, and measures the quality of the heuristics generated by different LLMs. Researchers and practitioners working on applying LLMs to solve difficult optimization tasks would use this to benchmark and compare different LLM approaches.