LLaMEA
Large Language Evolutionary Algorithm for the automatic design of algorithms.
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.
Key features of LLaMEA include:
-
Automated Algorithm Generation: Utilizes GPT models to create and enhance algorithms automatically.
-
Performance Evaluation: Integrates with IOHexperimenter and other evaluators for real-time feedback, guiding the evolutionary process.
-
Customizable Evolution Strategies: Allows configuration of strategies to effectively explore algorithmic design spaces.
-
Extensible and Modular Design: Offers flexibility for users to incorporate other models and evaluation tools.
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
Publications 15
-
Methodology
LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics
ACM DL ↗
-
Methodology
In-the-loop hyper-parameter optimization for LLM-based automated design of heuristics
ACM DL ↗
-
Methodology
Controlling the mutation in large language models for the efficient evolution of algorithms
Springer ↗
-
Methodology
LLaMEA-BO: A Large Language Model Evolutionary Algorithm for Automatically Generating Bayesian Optimization Algorithms
arXiv ↗
-
Methodology
Large Language Models and Evolutionary Computation: A Critical Review of Bidirectional Interaction, Automated Algorithm Design, and Co-adaptive Systems
ScienceDirect ↗
-
Methodology
LLaMEA-SAGE: Guiding Automated Algorithm Design with Structural Feedback from Explainable AI
arXiv ↗
-
Methodology
LLM-Driven Evolutionary Generation of Multi-Objective Bayesian Optimization Algorithms
arXiv ↗
-
Benchmarking & analysis
Code evolution graphs: Understanding large language model driven design of algorithms
ACM DL ↗
-
Benchmarking & analysis
BLADE: Benchmark suite for LLM-driven Automated Design and Evolution of iterative optimisation heuristics
ACM DL ↗
-
Benchmarking & analysis
Behaviour Space Analysis of LLM-driven Meta-heuristic Discovery
arXiv ↗
-
Benchmarking & analysis
From Heuristic Selection to Automated Algorithm Design: LLMs Benefit from Strong Priors
arXiv ↗
-
Applications
Optimizing Photonic Structures with Large Language Model Driven Algorithm Discovery
ACM DL ↗
-
Applications
Landscape-aware Automated Algorithm Design: An Efficient Framework for Real-world Optimization
arXiv ↗
-
Applications
LLM Driven Design of Continuous Optimization Problems with Controllable High-level Properties
arXiv ↗
-
Applications
Evolving Executable Pipeline Programs for AutoML with Language Models
arXiv ↗
