Evolutionary Computation and Large Language Models: A Survey of Methods, Synergies, and Applications

TL;DR

This survey reviews how evolutionary computation and large language models can synergistically enhance AI through mutual optimization, automation, and application across various domains, highlighting their integration, benefits, and challenges.

Contribution

It provides a comprehensive overview of the intersection between EC and LLMs, detailing methods, applications, and future research directions for their combined use.

Findings

EC techniques improve LLM prompt engineering and architecture search.

LLMs automate the design and tuning of evolutionary algorithms.

Emerging co-evolutionary frameworks show promising applications.

Abstract

Integrating Large Language Models (LLMs) and Evolutionary Computation (EC) represents a promising avenue for advancing artificial intelligence by combining powerful natural language understanding with optimization and search capabilities. This manuscript explores the synergistic potential of LLMs and EC, reviewing their intersections, complementary strengths, and emerging applications. We identify key opportunities where EC can enhance LLM training, fine-tuning, prompt engineering, and architecture search, while LLMs can, in turn, aid in automating the design, analysis, and interpretation of ECs. The manuscript explores the synergistic integration of EC and LLMs, highlighting their bidirectional contributions to advancing artificial intelligence. It first examines how EC techniques enhance LLMs by optimizing key components such as prompt engineering, hyperparameter tuning, and architecture search, demonstrating how evolutionary methods automate and refine these processes. Secondly, the survey investigates how LLMs improve EC by automating metaheuristic design, tuning evolutionary algorithms, and generating adaptive heuristics, thereby increasing efficiency and scalability. Emerging co-evolutionary frameworks are discussed, showcasing applications across diverse fields while acknowledging challenges like computational costs, interpretability, and algorithmic convergence. The survey concludes by identifying open research questions and advocating for hybrid approaches that combine the strengths of EC and LLMs.