用大模型自动配置优化算法，省去人工调参
Large Language Model-Driven Surrogate-Assisted Evolutionary Algorithm for Expensive Optimization
- 用大模型动态选择最优代理模型和采样策略
- 在标准测试集上超越多个顶尖优化算法
- 适合需要高效求解昂贵目标函数的科研与工程场景
代理辅助进化算法（SAEA）是解决高成本优化任务的关键工具，其效率高度依赖于代理模型和填充采样准则的选择。然而，设计有效的动态选择策略既费时又需大量领域知识。本文提出LLM-SAEA，一种创新方法，利用大语言模型（LLM）在线配置代理模型和填充采样准则。具体而言，LLM-SAEA构建了协作专家框架：一个LLM作为评分专家（LLM-SE），根据优化表现对代理模型和采样准则打分；另一个LLM作为决策专家（LLM-DE），结合得分与当前优化状态，选择合适配置。实验结果表明，LLM-SAEA在标准测试案例中优于多个现有先进算法。源代码已公开于 https://github.com/ForrestXie9/LLM-SAEA。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。