A General Genetic Algorithm Using Natural Language Evolutionary Operators

Stenzel, Gerhard; Gerner, Sarah; Kölle, Michael; Zorn, Maximilian und Gabor, Thomas (2025): A General Genetic Algorithm Using Natural Language Evolutionary Operators. GECCO 2025, Genetic and Evolutionary Computation Conference, Málaga, Spain, 14. Juli 2025 - 18. Juli 2025. Ochoa, Gabriela (Hrsg.): In: GECCO '25 Companion: Proceedings of the Genetic and Evolutionary Computation Conference Companion, New York, NY, USA: Association for Computing Machinery. S. 699-702

Abstract

By employing large language models (LLMs) we build a general genetic algorithm, i.e., a genetic algorithm (GA) that can solve various domains without any changes to its algorithmic components. Our approach requires only a problem description in natural language and a black-box fitness function and can then handle any type of data via natural-language-based evolutionary operators that call an LLM to compute their application. The relevant prompts for the operators can be human-designed or self-optimized with similar performance results. Compared to the only other generalist GA approach, i.e., asking an LLM to write a new specific GA, our natural-language-based genetic algorithm (NaLaGA) offers not only a better class of safety (since no LLM-generated code is executed by NaLaGA) but also greatly improved results in the two example domains ``Schwefel'' and ``grid world maze''.

• Dokumententyp: Konferenzbeitrag (Poster)
• Keywords: toappear
• Fakultät: Mathematik, Informatik und Statistik > Informatik
• Themengebiete: 000 Informatik, Informationswissenschaft, allgemeine Werke > 004 Informatik
• ISBN: 979-8-4007-1464-1
• Ort: New York, NY, USA
• Sprache: Englisch