G-LNS：基于大语言模型的自动启发式设计之生成式大邻域搜索

G-LNS: Generative Large Neighborhood Search for LLM-Based Automatic Heuristic Design

February 9, 2026

作者: Baoyun Zhao, He Wang, Liang Zeng

cs.AI

摘要

尽管大语言模型（LLMs）在自动启发式设计（AHD）领域展现出潜力，现有方法通常将AHD构建为构造型优先级规则或参数化局部搜索指导，从而将搜索空间限制在固定的启发式形式内。此类设计对结构探索的能力有限，难以在复杂组合优化问题（COPs）中跳出深度局部最优解。本文提出G-LNS——一种生成式进化框架，将基于LLM的AHD扩展至大邻域搜索（LNS）算子的自动化设计。与先前孤立演化启发式的方法不同，G-LNS利用LLM协同演化紧密耦合的破坏算子与修复算子对。通过合作式评估机制显式捕捉算子间的交互作用，从而发现能够协同实现有效结构破坏与重构的互补逻辑。在旅行商问题（TSP）和带容量车辆路径问题（CVRP）等复杂COP基准上的大量实验表明，G-LNS显著优于基于LLM的AHD方法及传统强求解器。所发现的启发式不仅能在有限计算资源下获得接近最优的解，还在多样化的未知实例分布上展现出强鲁棒性。

English

While Large Language Models (LLMs) have recently shown promise in Automated Heuristic Design (AHD), existing approaches typically formulate AHD around constructive priority rules or parameterized local search guidance, thereby restricting the search space to fixed heuristic forms. Such designs offer limited capacity for structural exploration, making it difficult to escape deep local optima in complex Combinatorial Optimization Problems (COPs). In this work, we propose G-LNS, a generative evolutionary framework that extends LLM-based AHD to the automated design of Large Neighborhood Search (LNS) operators. Unlike prior methods that evolve heuristics in isolation, G-LNS leverages LLMs to co-evolve tightly coupled pairs of destroy and repair operators. A cooperative evaluation mechanism explicitly captures their interaction, enabling the discovery of complementary operator logic that jointly performs effective structural disruption and reconstruction. Extensive experiments on challenging COP benchmarks, such as Traveling Salesman Problems (TSP) and Capacitated Vehicle Routing Problems (CVRP), demonstrate that G-LNS significantly outperforms LLM-based AHD methods as well as strong classical solvers. The discovered heuristics not only achieve near-optimal solutions with reduced computational budgets but also exhibit robust generalization across diverse and unseen instance distributions.