Learning Differential Evolution Mutation Strategies via Performance-Driven Large Language Models

Abstract

We propose an LLM-driven framework to generate and iteratively refine Differential Evolution mutation operators via structured, performance-based feedback. Starting from standard DE strategies (e.g., DE/rand/*, DE/best/*, current-to-rand/1, JADE, Union DE), the LLM proposes new operators, evaluates them with quantitative indicators, and uses the best as a reference for the next refinement cycle; we also compare different LLMs. Experiments on BBOB (30D/40D, 30 runs) show the feedback loop yields mutation strategies that outperform classical DE operators and LLM-generated variants without feedback.