OpenEvolve: Combining LLMs with Evolutionary Search for Algorithm Discovery

Summary

OpenEvolve is an open-source evolutionary coding agent that integrates large language models (LLMs) into a quality-diversity search framework for algorithm discovery. The system uses LLM-guided edits to generate candidate programs within an evolutionary framework, aiming to teach machines to discover algorithms through evolution rather than traditional hand-crafted heuristics or gradient-based optimization. The approach represents a novel method for algorithmic discovery by combining the creative potential of LLMs with evolutionary search techniques.