Evolutionary thoughts: integration of large language models and evolutionary algorithms

TL;DR

This paper explores integrating Large Language Models with Evolutionary Algorithms to enhance search efficiency and solution quality in complex problem spaces, addressing limitations of LLM reasoning and computational challenges of EAs.

Contribution

It introduces a novel framework combining LLMs with EAs, including an efficient evaluation method and a focused search strategy, improving solution quality in complex tasks.

Findings

LLMs enhance candidate solution generation.

The framework improves search efficiency.

Empirical results show better outcomes with the integrated approach.

Abstract

Large Language Models (LLMs) have unveiled remarkable capabilities in understanding and generating both natural language and code, but LLM reasoning is prone to hallucination and struggle with complex, novel scenarios, often getting stuck on partial or incorrect solutions. However, the inherent ability of Evolutionary Algorithms (EAs) to explore extensive and complex search spaces makes them particularly effective in scenarios where traditional optimization methodologies may falter. However, EAs explore a vast search space when applied to complex problems. To address the computational bottleneck of evaluating large populations, particularly crucial for complex evolutionary tasks, we introduce a highly efficient evaluation framework. This implementation maintains compatibility with existing primitive definitions, ensuring the generation of valid individuals. Using LLMs, we propose an enhanced evolutionary search strategy that enables a more focused exploration of expansive solution spaces. LLMs facilitate the generation of superior candidate solutions, as evidenced by empirical results demonstrating their efficacy in producing improved outcomes.