发表机构
Southern University of Science and Technology; The Hong Kong University of Science and Technology（南方科技大学; 香港科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出MuEvo框架，结合动态组件管理与LLM驱动协同演化，在四类组合优化领域的实验显示其优于现有LLM-AHD方法，可改进人工设计的优化框架。
AI 中文摘要
基于大语言模型的自动启发式设计（LLM-AHD）在为组合优化问题发现有效启发式方面展现出强大潜力。然而，现有方法主要优化单一启发式，而实际优化框架常依赖多个相互作用的组件。直接扩展单一启发式方法颇具挑战，因为早期组件选择可能忽略后期有潜力的组件，而独立演化则会忽略组件间的依赖关系。我们提出MuEvo，这是一个在集成级反馈下演化启发式集成的LLM驱动框架。MuEvo结合了动态组件管理与LLM驱动的协同演化：动态组件管理使用短预算探测和可逆生命周期，在整个搜索过程中调整组件优先级；LLM驱动的协同演化则通过多集成评估、跨组件信息共享、关系引导的成对演化和自适应预算分配来协调组件种群。我们在选择超启发式和组件化蚁群优化的四个组合优化领域评估MuEvo。结果表明，MuEvo始终改进人工设计的框架，且优于最先进LLM-AHD方法的代表性多组件扩展，证明其在控制器介导的启发式池和功能差异化算法组件上均有效。
英文摘要
Large language model-based automated heuristic design (LLM-AHD) has shown strong potential in discovering effective heuristics for combinatorial optimization problems. However, existing methods primarily optimize a single heuristic, whereas practical optimization frameworks often rely on multiple interacting components. Directly extending single-heuristic methods is challenging because early component selection can overlook components with late potential, while independent evolution ignores inter-component dependencies. We propose MuEvo, an LLM-driven framework for evolving heuristic ensembles under ensemble-level feedback. MuEvo combines Dynamic Component Management, which uses short-budget probing and a reversible lifecycle to revise component priorities throughout the search, with LLM-Driven Co-Evolution, which coordinates component populations through Multi-Ensemble Evaluation, Cross-Component Information Sharing, Relation-Guided Pair Evolution, and Adaptive Budget Allocation. We evaluate MuEvo on selection hyper-heuristics and componentized ant colony optimization across four combinatorial optimization domains. Results show that MuEvo consistently improves human-designed frameworks and outperforms representative multi-component extensions of state-of-the-art LLM-AHD methods, demonstrating its effectiveness across both controller-mediated heuristic pools and functionally differentiated algorithmic components.
Comments30 pages, 4 figures, 16 tables
