Dynamic flexible assembly flow shop scheduling with multi-product delivery is a critical combinatorial problem, characterized by kitting supply and machine flexibility. Genetic programming is widely used to automatically generate dispatching rules, enabling responsive scheduling that reduces manual effort while meeting high responsiveness demands. However, these methods are dependent on fixed terminal sets and have weak interpretability. In this article, we develop an evolving dispatching rules framework (EvoDR) that leverages the semantic understanding and generation capabilities of large language models to achieve cross-domain integration of algorithm design and scheduling knowledge. Firstly, multi-stage assembly supply decisions are modeled as priority sorting of directed edges based on heterogeneous graphs. A dual-expert co-evolution mechanism is implemented, where LLM-A generates code while LLM-S conducts scheduling analysis and reflection. Guided by improvements in hybrid evaluation, adaptive rules that fit dynamic features are continuously evolved. Experimental results show that the EvoDR achieves lower average tardiness than state-of-the-art approaches. In 24 scenarios with different resource configurations and disturbance levels totaling 480 instances, it consistently outperforms expert-designed competitors, demonstrating superior robustness.

翻译：具有多产品交付的动态柔性装配流水车间调度是一个关键的组合优化问题，其特点在于物料齐套供应和机器柔性。遗传规划方法被广泛用于自动生成调度规则，以实现响应式调度，在满足高响应性需求的同时减少人工投入。然而，这些方法依赖于固定的终端集，且可解释性较弱。本文提出了一种调度规则进化框架（EvoDR），利用大语言模型的语义理解与生成能力，实现算法设计与调度知识的跨域融合。首先，将多阶段装配供应决策建模为基于异构图的有向边优先级排序。其次，实现双专家协同进化机制，其中LLM-A负责生成代码，而LLM-S负责进行调度分析与反思。在混合评估方法改进的指导下，适应动态特征的自适应规则得以持续进化。实验结果表明，EvoDR相较于现有最优方法实现了更低的平均延迟。在涵盖24种不同资源配置与扰动水平的480个实例场景中，该方法始终优于专家设计的对比方法，展现出卓越的鲁棒性。