发表机构
Antai College of Economics and Management, Shanghai Jiao Tong University; Global Institute of Future Technology, Shanghai Jiao Tong University（上海交通大学安泰经济与管理学院; 上海交通大学未来技术学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出LLM驱动的启发式组件联合生成框架，将耦合的启发式组件协同进化，在TSP和CVRP基准上取得优异结果，实现跨实例迁移。
AI 中文摘要
组合优化的启发式设计仍高度依赖专家知识，而现有大语言模型（LLM）增强的进化方法通常仅进化孤立的算法组件，即便某一组件会决定另一组件运行时的搜索状态。本文提出由LLM驱动的启发式组件联合生成框架（LLM-HCJG），这是一种基于种群的框架，可在共享设计蓝图下联合生成并协同进化相互依赖的启发式组件。将其应用于引导式局部搜索（GLS）时，LLM-HCJG将解初始化与惩罚构造耦合，并将生成的配对嵌入增强型在线搜索机制。所得到的形式进一步从旅行商问题（TSP）迁移至容量受限车辆路径问题（CVRP）。理论分析确立了两个组件间不可分离的状态转换效应及生成一致性优势。在合成实例与41个公开的TSPLIB/CVRPLIB基准测试中，LLM-HCJG始终取得较低的最优性间隙，其中29个TSPLIB实例中的28个、12个CVRPLIB实例均取得最优或并列最优结果。消融与结构分析进一步表明，这些增益与组件间的兼容性和对齐相关，而非孤立组件的重组。这些结果支持在有限样本、适度成本的训练下，在所评估的路由设置中实现有效的跨实例迁移。
英文摘要
Heuristic design for combinatorial optimization remains heavily reliant on expert knowledge, while existing large language model (LLM)-enhanced evolutionary methods typically evolve isolated algorithmic components, even when one determines the search state on which another operates. This paper proposes LLM-driven Heuristic Components Joint Generation (LLM-HCJG), a population-based framework that jointly generates and co-evolves interdependent heuristic components under a shared design blueprint. Applied to guided local search (GLS), LLM-HCJG couples solution initialization with penalty construction and embeds the generated pair into an enhanced online search mechanism. The resulting form is further transferred from the traveling salesman problem (TSP) to the capacitated vehicle routing problem (CVRP). Theoretical analysis establishes the non-separable state-transition effects between the two components and the advantage in generation consistency. Across synthetic instances and 41 public TSPLIB/CVRPLIB benchmarks, LLM-HCJG attains consistently low optimality gaps, including best or tied-best results on 28 of 29 TSPLIB instances and all 12 CVRPLIB instances. Ablation and structural analyses further indicate that these gains are associated with cross-component compatibility and alignment rather than isolated-component recombination. These results support effective cross-instance transfer within the evaluated routing settings under limited-sample, modest-cost training.
