用模块化框架让大模型自动优化启发式算法，效果显著提升。
Heuristic Search as Language-Guided Program Optimization
- 将启发式算法设计拆解为评估、反馈、优化三步，可独立改进
- 在4个真实场景中测试，性能最高提升0.17（QYI指标）
- 兼容现有方法，可模块化升级，适合算法研发与自动化设计
近年来，大语言模型（LLMs）推动了组合优化中的自动化启发式设计（AHD）发展。然而，现有发现流程常需大量人工试错或依赖领域知识来适应新问题或复杂场景，根源在于内部机制高度耦合，难以系统性优化。为此，我们提出一种结构化框架，将启发式发现过程显式分解为三个模块化阶段：前向评估、反向分析反馈和程序更新。该分离提供清晰迭代抽象，支持各组件的独立优化。我们在四个不同真实世界的组合优化领域验证该框架，均优于基线方法，在未见过的测试集上最高实现0.17的QYI提升。最后，我们证明多个主流AHD方法均为本框架的特例；通过将其整合进我们的结构化流水线，可模块化升级组件并显著提升性能。
原文摘要 · Abstract (English)
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.
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。