用大模型设计更鲁棒的启发式算法，显著提升最差情况表现。
Robust Heuristic Algorithm Design with LLMs
- 让大模型分析启发式算法失效的实例并给出原因
- 在输入空间不同区域针对性优化，使最差性能提升28倍
- 保持原有运行时间，适合需要稳定性能的场景
我们提出，若在启发式算法设计中结合大模型，并加入对其失效原因的解释与修复建议，可生成更鲁棒、性能更强的启发式算法。即使采用简单方法——（1）让大模型接触启发式算法表现不佳的实例；（2）解释其失效原因；（3）针对输入空间的不同区域进行专门化设计——也能显著优于现有技术。所生成的启发式算法相比FunSearch在最差情况性能上提升约28倍，同时改善平均性能并保持原有运行时间。
原文摘要 · Abstract (English)
We posit that we can generate more robust and performant heuristics if we augment approaches using LLMs for heuristic design with tools that explain why heuristics underperform and suggestions about how to fix them. We find even simple ideas that (1) expose the LLM to instances where the heuristic underperforms; (2) explain why they occur; and (3) specialize design to regions in the input space, can produce more robust algorithms compared to existing techniques~ -- ~the heuristics we produce have a $\sim28\times$ better worst-case performance compared to FunSearch, improve average performance, and maintain the runtime.
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。