When Large Language Models Meet Evolutionary Algorithms: Potential Enhancements and Challenges
Research · 2025-01 · 8
DOI: 10.34133/research.0646 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Research, online erschienen am 27.03.2025. Verfasst von Chao Wang und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence, Xidian University, Xi'an 710071, Shaanxi, China. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 112 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Pre-trained large language models (LLMs) exhibit powerful capabilities for generating natural text. Evolutionary algorithms (EAs) can discover diverse solutions to complex real-world problems. Motivated by the common collective and directionality of text generation and evolution, this paper first illustrates the conceptual parallels between LLMs and EAs at a micro level, which includes multiple one-to-one key characteristics: token representation and individual representation, position encoding and fitness shaping, position embedding and selection, Transformers block and reproduction, and model training and parameter adaptation. These parallels highlight potential opportunities for technical advancements in both LLMs and EAs. Subsequently, we analyze existing interdisciplinary research from a macro perspective to uncover critical challenges, with a particular focus on evolutionary fine-tuning and LLM-enhanced EAs. These analyses not only provide insights into the evolutionary mechanisms behind LLMs but also offer potential directions for enhancing the capabilities of artificial agents.
Autor:innen und Institutionen
- School of Artificial Intelligence, Xidian University, Xi'an 710071, Shaanxi, China.
ORCID-Profile: Chao Wang, Licheng Jiao
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Wang, C., Zhao, J., Jiao, L., Li, L., Liu, F., & Yang, S. (2025). When Large Language Models Meet Evolutionary Algorithms: Potential Enhancements and Challenges. Research, 8. https://doi.org/10.34133/research.0646
Vancouver
Wang C, Zhao J, Jiao L, Li L, Liu F, Yang S. When Large Language Models Meet Evolutionary Algorithms: Potential Enhancements and Challenges. Research. 2025;8. doi:10.34133/research.0646
BibTeX
@article{Wang2025,
author = {Wang, Chao and Zhao, Jiaxuan and Jiao, Licheng and Li, Lingling and Liu, Fang and Yang, Shuyuan},
title = {When Large Language Models Meet Evolutionary Algorithms: Potential Enhancements and Challenges},
journal = {Research},
year = {2025},
volume = {8},
doi = {10.34133/research.0646}
}
EUVIMED