Evolutionary thoughts: integration of large language models and evolutionary algorithms

2025-05-09

AI Summary

Large language models (LLMs) suffer from hallucination and premature convergence to local optima on complex, novel tasks, while evolutionary algorithms (EAs) face computational bottlenecks when evaluating large populations. To address these dual challenges, this paper proposes an LLM-driven enhanced evolutionary search framework. It tightly integrates LLMs into the EA pipeline: first, prompt engineering guides the LLM to generate high-quality, semantically coherent candidate solutions, improving search directionality; second, a lightweight, semantics-based individual validation mechanism replaces costly full-execution evaluation, drastically reducing computational overhead. Experiments across diverse complex reasoning and code generation benchmarks demonstrate that the framework significantly outperforms baseline methods in solution correctness, robustness, and diversity—achieving more efficient and reliable global optimization.

Technology Category

• Search and Optimization: Evolutionary Computation
• Machine Learning: Large Multimodal Models (LMMs)
• Constraint Satisfaction and Optimization: Search

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• LLMs struggle with complex novel scenarios and hallucination
• EAs face computational bottlenecks in large search spaces
• Integrating LLMs and EAs enhances evolutionary search efficiency

Innovation

• Integration of LLMs and EAs for enhanced problem-solving
• Efficient evaluation framework for large evolutionary populations
• LLM-enhanced evolutionary search for superior candidate solutions