用大模型改进优化算法，让AI替人类设计更优解法
Improving Existing Optimization Algorithms with LLMs
- 用大模型生成优化算法的新启发式策略
- GPT-4o设计的策略优于人工设计的原始算法
- 在更大更密集图上优势更明显，适合算法研究者
将大型语言模型（LLMs）融入优化领域产生了强大的协同效应，开启了新的研究机遇。本文探讨了如何利用LLMs提升现有优化算法的性能。借助其预训练知识，我们展示了LLMs提出创新启发式变体和实现策略的能力。为验证该方法，我们采用了一种复杂的组合优化混合元启发式算法——构造、合并、求解与适应（CMSA），该算法在解的构建阶段引入启发式策略。实验结果表明，由GPT-4o提出的替代启发式策略优于原算法中专家设计的启发式，且在更大、更密集的图上性能差距进一步扩大。
原文摘要 · Abstract (English)
The integration of Large Language Models (LLMs) into optimization has created a powerful synergy, opening exciting research opportunities. This paper investigates how LLMs can enhance existing optimization algorithms. Using their pre-trained knowledge, we demonstrate their ability to propose innovative heuristic variations and implementation strategies. To evaluate this, we applied a non-trivial optimization algorithm, Construct, Merge, Solve and Adapt (CMSA) -- a hybrid metaheuristic for combinatorial optimization problems that incorporates a heuristic in the solution construction phase. Our results show that an alternative heuristic proposed by GPT-4o outperforms the expert-designed heuristic of CMSA, with the performance gap widening on larger and denser graphs. Project URL: https://imp-opt-algo-llms.surge.sh/
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。