Exploring Automated Algorithm Design Synergizing Large Language Models and Evolutionary Algorithms: Survey and Insights
Evolutionary Computation · 29.05.2026 · 34 (2) · 167-194
DOI: 10.1162/evco.a.370 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Evolutionary Computation, online erschienen am 29.05.2026. Verfasst von He Yu und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence, Xidian University, 2 South Taibai Road, Xi'an, Shaanxi 710071, China yuhe001@stu.xidian.edu.cn. Hauptthemen laut MEDLINE: Algorithms, Large Language Models. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 79 Literaturangaben.
Abstract (Originalsprache)
Designing algorithms for optimization problems, no matter heuristic or metaheuristic, often relies on manual design and domain expertise, limiting their scalability and adaptability. The integration of Large Language Models (LLMs) and Evolutionary Algorithms (EAs) presents a promising new way to overcome these limitations to make optimization be more automated, where LLMs function as dynamic agents capable of generating, refining, and interpreting optimization strategies, while EAs explore complex searching spaces efficiently through evolutionary operators. Since this synergy enables a more efficient and creative searching process, we first review important developments in this direction, and then summarize an LLM-EA paradigm for automated optimization algorithm design. We conduct an in-depth analysis on innovative methods for four key EA modules, namely, individual representation, selection, variation operators, and fitness evaluation, addressing challenges related to optimization algorithm design, particularly from the perspective of LLM prompts, analyzing how the prompt flows evolving with the evolutionary process, adjusting based on evolutionary feedback (e.g., population diversity, convergence rate). Furthermore, we analyze how LLMs, through flexible prompt-driven roles, introduce semantic intelligence into fundamental EA characteristics, including diversity, convergence, adaptability, and scalability. Our systematic review and thorough analysis into the paradigm can help researchers better understand the current research and boost the development of synergizing LLMs with EAs for automated optimization algorithm design.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Artificial Intelligence, Xidian University, 2 South Taibai Road, Xi'an, Shaanxi 710071, China yuhe001@stu.xidian.edu.cn.
- Guangzhou Institute of Technology, Xidian University, Knowledge City, Guangzhou, Guangdong 510555, China.
- School of Artificial Intelligence, Xidian University, 2 South Taibai Road, Xi'an, Shaanxi 710071, China neouma@mail.xidian.edu.cn.
Zitieren
APA
Yu, H., & Liu, J. (2026). Exploring Automated Algorithm Design Synergizing Large Language Models and Evolutionary Algorithms: Survey and Insights. Evolutionary Computation, 34(2), 167-194. https://doi.org/10.1162/evco.a.370
Vancouver
Yu H, Liu J. Exploring Automated Algorithm Design Synergizing Large Language Models and Evolutionary Algorithms: Survey and Insights. Evolutionary Computation. 2026;34(2):167-194. doi:10.1162/evco.a.370
BibTeX
@article{Yu2026,
author = {Yu, He and Liu, Jing},
title = {Exploring Automated Algorithm Design Synergizing Large Language Models and Evolutionary Algorithms: Survey and Insights},
journal = {Evolutionary Computation},
year = {2026},
volume = {34},
number = {2},
pages = {167--194},
doi = {10.1162/evco.a.370}
}
EUVIMED