返回
Autonomous Multiobjective Optimization Using Large Language Model
DOI:10.1109/TEVC.2025.3561001.png)
摘要
En 中文
Multiobjective optimization problems (MOPs) are ubiquitous in real-world applications, presenting a complex challenge of balancing multiple conflicting objectives. Traditional multiobjective evolutionary algorithms (MOEAs), though effective, often rely on domain-specific expertise for improved optimization performance, hindering adaptability to unseen MOPs. In recent years, the large language models (LLMs) has revolutionized software engineering by enabling the autonomous generation and refinement of programs. Leveraging this breakthrough, we propose a new LLM-based framework that autonomously designs MOEAs for solving MOPs. The proposed framework includes a robust testing module to refine the generated MOEA through error-driven dialogue with LLMs, a dynamic selection strategy along with informative prompting-based crossover and mutation to fit textual optimization pipeline. Our approach facilitates the design of MOEA without the extensive demands for expert intervention, thereby speeding up the innovation of MOEA. Empirical studies across various MOP categories validate the robustness and superior performance of our proposed framework.
Keyword:
Automatic algorithm design
large language model
multiobjective optimization
期刊
IF:
12
论文数:
2.0K
被引数:
3.1W
机构
引用论文
Zhang, R., Liu, F., Lin, X., Wang, Z., Lu, Z., Zhang, Q., 2024. Understanding the importance of evolutionary search in automated heuristic design with large language models. In: International Conference on Parallel Problem Solving from Nature. Springer, pp. 185–202.张, R., 刘, F., 林, X., 王, Z., 陆, Z., 张, Q., 2024. 理解进化搜索在大型语言模型自动化启发式设计中的重要性。载于: 从自然中学习并行问题解决的国际会议。Springer, 第185-202页。
Mathematical discoveries from program search with large language models使用大型语言模型进行程序搜索的数学发现
Nature
IF48.5

