Open and closed source models for LLM-generated metaheuristics solving engineering optimization problem

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F70883521%3A28140%2F25%3A63599698" target="_blank" >RIV/70883521:28140/25:63599698 - isvavai.cz</a>

Result on the web

<a href="http://dx.doi.org/10.1007/978-3-031-90065-5_23" target="_blank" >http://dx.doi.org/10.1007/978-3-031-90065-5_23</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-90065-5_23" target="_blank" >10.1007/978-3-031-90065-5_23</a>

Result language

angličtina

Original language name

Open and closed source models for LLM-generated metaheuristics solving engineering optimization problem

Original language description

This paper explores the applicability of generative AI (genAI), specifically Large Language Models (LLMs), for the automatic generation and configuration of metaheuristic algorithms to address a real-world engineering problem: the optimal parameter estimation of time-delay systems in interconnected heating-cooling loops. The study introduces a pioneering workflow and iterative architecture with feedback within the emerging field of genAI-driven optimization for real optimization problems, eliminating the need for manually crafted or modified algorithms. This automated system empowers domain experts in engineering to solve complex optimization problems with minimal knowledge of optimization algorithms, lowering the barrier to entry for sophisticated algorithm use. We demonstrate how LLMs can generate effective optimizers under conditions like connstrained optimization problems where the solution lies near the boundaries of the search space. Four state-of-the-art LLMs (closed and open-sourced) have been selected for experiments. These are GPT-4o, GPT-4o mini, Claude Sonnet 3.5 and Llama 3.1. All studied LLMs generated metaheuristics that outperformed the initialization baseline optimization method (Random Search and CMA-ES). Notably, the Claude Sonnet 3.5 model generated a metaheuristic with the best mean results, almost matching the performance of the tuned state-of-the-art DISH algorithm, as an example of adaptive Differential Evolution.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/GF21-45465L" target="_blank" >GF21-45465L: Metaheuristic-based parametric optimization of time-delay models and control systems</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Lecture Notes in Computer Science

ISBN

978-3-031-90064-8

ISSN

0302-9743

e-ISSN

1611-3349

Number of pages

14

Pages from-to

372-385

Publisher name

Springer

Place of publication

Cham

Event location

Trieste

Event date

Apr 23, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—