Adaptive Large Neighborhood Search (ALNS) is a prominent metaheuristic and a widely adopted approach for production and logistics optimization. However, it has long relied on hand-crafted components built on expert experience, which makes development slow and costly to adapt to new problems. This paper proposes a closed-loop, large-language-model-driven evolutionary framework that decouples ALNS and automatically rebuilds all of its components. We break ALNS into seven key modules: destroy, repair, operator selection, weight update, initial solution construction, acceptance rule, and destroy-rate control, and evolve each module through a dedicated task. By incorporating the MAP-Elites mechanism, the framework maintains a multi-dimensional elite archive to simultaneously drive the evolution of solution quality and strategic diversity. On TSPLIB benchmarks, the evolved algorithms consistently outperform optimized classic ALNS baselines under both fixed-iteration and fixed-time limits. The gains are especially clear on large-scale instances, where the average optimality gap drops from 3.18% to 0.74%. Code analysis also uncovers several counterintuitive yet meaningful design patterns that emerged naturally during evolution, offering practical and theoretical insights for future ALNS design. Finally, comparisons across multiple language models highlight clear differences in their ability to support evolutionary algorithm design, helping guide model selection for real-world engineering use.

翻译：自适应大邻域搜索（ALNS）是一种重要的元启发式算法，也是生产与物流优化领域广泛采用的方法。然而，该方法长期依赖基于专家经验手工构建的组件，导致其开发过程缓慢且难以适应新问题，调整成本高昂。本文提出一种闭环式、大语言模型驱动的演化框架，该框架将ALNS解耦并自动重构其所有组件。我们将ALNS分解为七个关键模块：破坏、修复、算子选择、权重更新、初始解构建、接受规则和破坏率控制，并通过专用任务对每个模块进行演化。通过引入MAP-Elites机制，该框架维护了一个多维精英档案，以同时驱动解的质量与策略多样性的演化。在TSPLIB基准测试中，无论是固定迭代次数还是固定时间限制下，演化生成的算法均持续优于经过优化的经典ALNS基线方法。该优势在大规模算例上尤为显著，平均最优间隙从3.18%降至0.74%。代码分析还揭示了演化过程中自然涌现的若干反直觉却有意义的设计模式，为未来ALNS的设计提供了实践与理论启示。最后，多个语言模型间的对比突显了它们在支持演化算法设计能力上的显著差异，这有助于为实际工程应用中的模型选择提供指导。