Large Language Model-Driven Surrogate-Assisted Evolutionary Algorithm for Expensive Optimization

TL;DR

This paper introduces LLM-SAEA, a novel surrogate-assisted evolutionary algorithm that leverages large language models to dynamically select surrogate models and sampling criteria, significantly improving optimization efficiency for expensive problems.

Contribution

The paper presents a new LLM-based framework for automatically configuring SAEAs, reducing the need for manual design and domain expertise.

Findings

LLM-SAEA outperforms state-of-the-art algorithms on standard benchmarks.

The collaboration-of-experts framework effectively guides surrogate model and sampling criterion selection.

Experimental results validate the approach's superiority in expensive optimization tasks.

Abstract

Surrogate-assisted evolutionary algorithms (SAEAs) are a key tool for addressing costly optimization tasks, with their efficiency being heavily dependent on the selection of surrogate models and infill sampling criteria. However, designing an effective dynamic selection strategy for SAEAs is labor-intensive and requires substantial domain knowledge. To address this challenge, this paper proposes LLM-SAEA, a novel approach that integrates large language models (LLMs) to configure both surrogate models and infill sampling criteria online. Specifically, LLM-SAEA develops a collaboration-of-experts framework, where one LLM serves as a scoring expert (LLM-SE), assigning scores to surrogate models and infill sampling criteria based on their optimization performance, while another LLM acts as a decision expert (LLM-DE), selecting the appropriate configurations by analyzing their scores along with the current optimization state. Experimental results demonstrate that LLM-SAEA outperforms several state-of-the-art algorithms across standard test cases. The source code is publicly available at https://github.com/ForrestXie9/LLM-SAEA.