发表机构
TU Wien（维也纳技术大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究构建了适用于MiniZinc格式问题的自动流程，引导LLM生成图生成器以辅助SLIM框架，在20个MiniZinc竞赛问题上使算法选择胜率大幅提升，证明LLM语义生成可实现高效的约束优化自动特征提取。
AI 中文摘要
大规模邻域搜索通常会选择随机的决策变量子集进行迭代优化。为了高效求解不同问题，研究人员倾向于结合不同领域的结构特征设计变量选择策略。本文构建了一个对所有MiniZinc格式问题均适用的问题无关自动流程。通过向大语言模型（LLM）输入我们的语义指南，引导其生成一个图生成器，该生成器可将任意问题类型的实例映射为均匀加权图，其中节点代表决策变量，边代表约束关系。这些与问题无关的图指导我们的基于结构的局部改进框架（SLIM）进行变量选择。同时，加权图使所有问题实例能够共享相同的通用图表示，从中可提取相同的图特征并用于配置选择。我们在20个MiniZinc竞赛问题的实例上评估了该流程，发现算法选择相较于一次性Gurobi基线，实现了39.5%的平均问题加权胜率，是最佳单一配置（19.3%）的两倍多。配置与特征消融进一步将性能提升至44.0%，表明基于LLM的语义生成可为约束优化实现有效的自动结构提取和特征提取。
英文摘要
Large neighborhood search normally selects a random subset of decision variables for iterative optimization. To efficiently solve various problems, researchers tend to design variable selection strategies that take into account structural features across different domains. In this paper, we build an automatic pipeline that is problem-agnostic to all problems in the MiniZinc format. By prompting an LLM with our semantic guidelines, we guide the LLM to produce a graph generator that maps any instance of a problem type to a uniform weighted graph, where nodes represent decision variables and edges represent constraint relationships. These problem-agnostic graphs guide our structure-based local improvement (SLIM) framework for variable selection. Meanwhile, the weighted graph enables all problem instances to share the same generic graph representation, from which the same graph features can be extracted and used for configuration selection. We evaluated our pipeline on instances across 20 MiniZinc competition problems, finding that algorithm selection achieves a 39.6% average problem-weighted win rate against a one-shot Gurobi baseline, more than doubling the best single configuration (19.3%). A post-hoc configuration and a feature ablation indicate a headroom of up to 44.0%, demonstrating that LLM-based semantic generation enables effective automated structure and feature extraction for constraint optimization.
