Using LLM for automatic evolvement of metaheuristics from swarm algorithm SOMA

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F70883521%3A28140%2F24%3A63587659" target="_blank" >RIV/70883521:28140/24:63587659 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1145/3638530.3664181" target="_blank" >http://dx.doi.org/10.1145/3638530.3664181</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3638530.3664181" target="_blank" >10.1145/3638530.3664181</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Using LLM for automatic evolvement of metaheuristics from swarm algorithm SOMA

Popis výsledku v původním jazyce

This study investigates the use of the GPT-4 Turbo, a large language model, to enhance the Self-Organizing Migrating Algorithm (SOMA), specifically its All to All variant (SOMA-ATA). Utilizing the model&apos;s extensive context capacity for iterative prompting without feedback, we sought to autonomously generate superior algorithmic versions. Contrary to our initial hypothesis, the improvements did not progress linearly. Nevertheless, one iteration stood out significantly, consistently outperforming the baseline across various pairwise comparisons and showing a robust performance profile. This iteration&apos;s structure deviated substantially from traditional SOMA principles, underscoring the potential of large language models to create distinctive and effective algorithmic strategies. The results affirm the methodology&apos;s ability to produce high-performing algorithms without expert intervention, setting the stage for future research to integrate feedback mechanisms and conduct detailed code analyses to understand further the modifications made by the Large Language Models.

Název v anglickém jazyce

Using LLM for automatic evolvement of metaheuristics from swarm algorithm SOMA

Popis výsledku anglicky

This study investigates the use of the GPT-4 Turbo, a large language model, to enhance the Self-Organizing Migrating Algorithm (SOMA), specifically its All to All variant (SOMA-ATA). Utilizing the model&apos;s extensive context capacity for iterative prompting without feedback, we sought to autonomously generate superior algorithmic versions. Contrary to our initial hypothesis, the improvements did not progress linearly. Nevertheless, one iteration stood out significantly, consistently outperforming the baseline across various pairwise comparisons and showing a robust performance profile. This iteration&apos;s structure deviated substantially from traditional SOMA principles, underscoring the potential of large language models to create distinctive and effective algorithmic strategies. The results affirm the methodology&apos;s ability to produce high-performing algorithms without expert intervention, setting the stage for future research to integrate feedback mechanisms and conduct detailed code analyses to understand further the modifications made by the Large Language Models.

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

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

GECCO 2024 Companion - Proceedings of the 2024 Genetic and Evolutionary Computation Conference Companion

ISBN

979-8-4007-0495-6

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

2018-2022

Název nakladatele

Association for Computing Machinery, Inc

Místo vydání

New York

Místo konání akce

Melbourne

Datum konání akce

14. 7. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—