发表机构
Stern School of Business, New York University（纽约大学斯特恩商学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文探究大型语言模型能否为库存控制等明确定义的运筹学问题设计算法，发现最强模型gpt-5.6-sol的算法性能可匹配或优于现有最佳方法，前沿LLM可成为算法设计的重要经验基准。
AI 中文摘要
本文探究大型语言模型（LLMs）能否为明确定义的运筹学（OR）问题设计有效算法，研究对象包括库存控制、排队网络控制及 assortment 优化。我们评估了 LLM 的两种使用层级：层级1中，模型接收单个问题实例并返回该实例的解；层级2中，模型仅接收问题类描述和宽泛参数范围，返回映射实例参数到解的算法。人工输入极少：仅提供一个未调参的问题描述提示，模型可访问带有固定计算预算的 Python 沙盒工具。我们测试的最强模型 gpt-5.6-sol，在几乎所有评估实例上都匹配或优于现有最佳方法，即使在层级2（返回算法在评估实例前已固定）也成立。性能在间隔不足8个月发布的模型间大幅提升，表明该能力发展迅速。综上，对于本文研究的明确定义运筹问题，单次未调参的 LLM 查询即可产出可与专用方法匹敌的算法，这些结果表明，前沿 LLM 可成为明确定义 OR 问题算法设计的重要经验基准。
英文摘要
We ask whether large language models (LLMs) can design effective algorithms for well-specified operations research (OR) problems. We study inventory control, queueing network control, and assortment optimization. We evaluate two levels of LLM use: at level 1, the model receives one problem instance and returns a solution for that instance; at level 2, it receives only the problem class description and broad parameter ranges, and returns an algorithm that maps instance parameters to solutions. Human input is minimal: we give one untuned prompt that describes the problem, and the model has access to a Python sandbox tool with a fixed compute budget. The strongest model we test, gpt-5.6-sol, matches or outperforms the best existing method on almost all evaluated instances. This holds even at level 2, where the returned algorithm is fixed before seeing the evaluation instances. Performance also improves sharply across models released less than eight months apart, suggesting that this capability is moving quickly. Thus, for the well-specified operations problems we study, a single untuned LLM query can already produce algorithms competitive with specialized methods. These results suggest that frontier LLMs can be a serious empirical baseline for algorithm design in well-specified OR problems.
