LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics

TL;DR

This paper presents LLaMEA, a framework that uses GPT-based language models to automatically generate, mutate, and select optimization algorithms, achieving superior performance on benchmark problems without prior expert knowledge.

Contribution

LLaMEA introduces a novel evolutionary algorithm framework leveraging GPT models for automated algorithm generation and refinement, advancing the field of automated algorithm design.

Findings

Generated algorithms outperform state-of-the-art optimization methods on BBOB benchmarks.

Algorithms show competitive performance on higher-dimensional test functions.

Framework demonstrates feasibility of automated algorithm generation using LLMs.

Abstract

Large Language Models (LLMs) such as GPT-4 have demonstrated their ability to understand natural language and generate complex code snippets. This paper introduces a novel Large Language Model Evolutionary Algorithm (LLaMEA) framework, leveraging GPT models for the automated generation and refinement of algorithms. Given a set of criteria and a task definition (the search space), LLaMEA iteratively generates, mutates and selects algorithms based on performance metrics and feedback from runtime evaluations. This framework offers a unique approach to generating optimized algorithms without requiring extensive prior expertise. We show how this framework can be used to generate novel black-box metaheuristic optimization algorithms automatically. LLaMEA generates multiple algorithms that outperform state-of-the-art optimization algorithms (Covariance Matrix Adaptation Evolution Strategy and Differential Evolution) on the five dimensional black box optimization benchmark (BBOB). The algorithms also show competitive performance on the 10- and 20-dimensional instances of the test functions, although they have not seen such instances during the automated generation process. The results demonstrate the feasibility of the framework and identify future directions for automated generation and optimization of algorithms via LLMs.