启发式搜索作为语言引导的程序优化
Heuristic Search as Language-Guided Program Optimization
AI总结：
本文提出了一种结构化框架，通过分解启发式发现过程为模块化阶段，提升LLM驱动的自动启发式设计在组合优化中的性能。
摘要：
大型语言模型（LLMs）在过去几年中推动了组合优化（CO）中的自动启发式设计（AHD）的发展。然而，现有的发现管道往往需要大量的手动试错或依赖领域专业知识来适应新或复杂的问题。这源于紧密耦合的内部机制，限制了LLM驱动的设计过程的系统性改进。为了解决这一挑战，我们提出了一种结构化的LLM驱动AHD框架，明确将启发式发现过程分解为模块化阶段：评估的正向传递、分析反馈的反向传递以及程序细化的更新步骤。这种分离为迭代改进提供了清晰的抽象，并使各个组件的系统性改进成为可能。我们在四个多样的现实世界CO领域中验证了我们的框架，其中它一致优于基线方法，在未见过的测试集上实现了高达0.17的QYI改进。最后，我们展示了几种流行的AHD方法是我们的框架的受限实例。通过在我们的结构化管道中整合它们，我们可以模块化升级组件并显著提高其性能。
英文摘要：
Large Language Models (LLMs) have advanced Automated Heuristic Design (AHD) in combinatorial optimization (CO) in the past few years. However, existing discovery pipelines often require extensive manual trial-and-error or reliance on domain expertise to adapt to new or complex problems. This stems from tightly coupled internal mechanisms that limit systematic improvement of the LLM-driven design process. To address this challenge, we propose a structured framework for LLM-driven AHD that explicitly decomposes the heuristic discovery process into modular stages: a forward pass for evaluation, a backward pass for analytical feedback, and an update step for program refinement. This separation provides a clear abstraction for iterative refinement and enables principled improvements of individual components. We validate our framework across four diverse real-world CO domains, where it consistently outperforms baselines, achieving up to $0.17$ improvement in QYI on unseen test sets. Finally, we show that several popular AHD methods are restricted instantiations of our framework. By integrating them in our structured pipeline, we can upgrade the components modularly and significantly improve their performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
