Szczegóły publikacji
Opis bibliograficzny
Constructing differential evolution via LLM prompt chaining : a competition entry on competition on LLM-designed evolutionary algorithms at the Genetic and Evolutionary Computation Conference (GECCO) 2025 / Dominik Papaj, Tomasz Karpiński, Rohit SALGOTRA // W: GECCO'25 Companion [Dokument elektroniczny] : proceedings of the 2025 Genetic and Evolutionary Computation Conference Companion : July 14–18, 2025, Málaga, Spain. — Wersja do Windows. — Dane tekstowe. — New York : Association for Computing Machinery, 2025. — e-ISBN: 979-8-4007-1464-1. — S. 5–6. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 6, Abstr. — Publikacja dostępna online od: 2025-08-11
Autorzy (3)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 161858 |
|---|---|
| Data dodania do BaDAP | 2025-09-02 |
| Tekst źródłowy | URL |
| DOI | 10.1145/3712255.3735095 |
| Rok publikacji | 2025 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Creative Commons | |
| Wydawca | Association for Computing Machinery (ACM) |
| Konferencja | Genetic and Evolutionary Computations 2025 |
Abstract
This paper presents an extended abstract, designed as a competition entry on LLM-designed Evolutionary Algorithms. We present DEuLLM, a differential evolution (DE) constructed entirely through prompt engineering with the help of a large language model (LLM). DEuLLM integrates key advances in DE, such as success-historybased parameter adaptations, distance-based feedback, linear population size reduction, and careful boundary control, without any code design outside the LLM-driven dialogue. The development process demonstrates how iterative prompting can guide the design of a competitive optimizer from scratch through natural language interaction. The results show that our proposed DEuLLM is able to locate the global optimum for 15 out of 24 test problems.
