LLaMEA

LLaMEA

LLaMEA, or Large Language Model Evolutionary Algorithm, is an innovative framework developed by the XAI research group at NACO with the lead of Niki van Stein. It leverages large language models (LLMs), such as GPT-4, to automate the generation and refinement of algorithms such as metaheuristic optimizers. By iteratively evolving algorithms based on performance metrics and runtime evaluations, LLaMEA streamlines the optimization process without requiring extensive prior algorithmic knowledge.

See also the introductory Youtube video.

Key features of LLaMEA include:

This framework is particularly beneficial for both research and practical applications in fields where optimization is crucial. For more details, including installation instructions and usage guidelines, please visit the project’s Github Repository. In addition, a accompanying benchmarking framework with additional real-world problems and baselines is available in the BLADE Github Repository.

Awards

The research on LLaMEA and generated algorithms from LLaMEA have won the following prestiguous awards:

🥈 Silver Award at the GECCO 2025 Humies competition
🏅 Winner of the GECCO 2025 Any-Time Performance for Affine BBOB competition
🏅 Winner of the GECCO 2024 Any-Time Performance for Affine BBOB competition

Methodology

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

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

In-the-loop hyper-parameter optimization for LLM-based automated design of heuristics

In-the-loop hyper-parameter optimization for LLM-based automated design of heuristics

Controlling the mutation in large language models for the efficient evolution of algorithms

Controlling the mutation in large language models for the efficient evolution of algorithms

LLaMEA-BO: A Large Language Model Evolutionary Algorithm for Automatically Generating Bayesian Optimization Algorithms

LLaMEA-BO: Automatically Generating Bayesian Optimization Algorithms

Evolutionary Computation and Large Language Models: A Survey of Methods, Synergies, and Applications

Evolutionary Computation and Large Language Models: A Survey of Methods, Synergies, and Applications

Benchmarking and Analysis

Code evolution graphs: Understanding large language model driven design of algorithms

Code evolution graphs: Understanding large language model driven design of algorithms

BLADE: Benchmark suite for LLM-driven Automated Design and Evolution of iterative optimisation heuristics

BLADE: Benchmark suite for LLM-driven Automated Design and Evolution

Behaviour Space Analysis of LLM-driven Meta-heuristic Discovery

Behaviour Space Analysis of LLM-driven Meta-heuristic Discovery

Real World Applications

Optimizing Photonic Structures with Large Language Model Driven Algorithm Discovery

Optimizing Photonic Structures with Large Language Model Driven Algorithm Discovery

People involved:


Haoran Yin
Haoran Yin
Elena Raponi
Assistant Professor of Bayesian Optimization
Anna V. Kononova
Assistant Professor of Efficient Heuristic Optimization
Prof. Thomas Bäck
Professor of Natural Computing
Niki van Stein
Assistant Professor of Explainable AI