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

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

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

Projekt

<a href="/cs/project/GF21-45465L" target="_blank" >GF21-45465L: Metaheuristicky založená parametrická optimalizace modelů a řídicích systémů s dopravním zpožděním</a><br>

Návaznosti

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

Rok uplatnění

2025

Kód důvěrnosti údajů

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

Název statě ve sborníku

Lecture Notes in Computer Science

ISBN

978-3-031-90064-8

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

14

Strana od-do

372-385

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Trieste

Datum konání akce

23. 4. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—