Heuristic dispatching rules (HDRs) are widely regarded as effective methods for solving dynamic job shop scheduling problems (DJSSP) in real-world production environments. However, their performance is highly scenario-dependent, often requiring expert customization. To address this, genetic programming (GP) and gene expression programming (GEP) have been extensively used for automatic algorithm design. Nevertheless, these approaches often face challenges due to high randomness in the search process and limited generalization ability, hindering the application of trained dispatching rules to new scenarios or dynamic environments. Recently, the integration of large language models (LLMs) with evolutionary algorithms has opened new avenues for prompt engineering and automatic algorithm design. To enhance the capabilities of LLMs in automatic HDRs design, this paper proposes a novel population self-evolutionary (SeEvo) method, a general search framework inspired by the self-reflective design strategies of human experts. The SeEvo method accelerates the search process and enhances exploration capabilities. Experimental results show that the proposed SeEvo method outperforms GP, GEP, end-to-end deep reinforcement learning methods, and more than 10 common HDRs from the literature, particularly in unseen and dynamic scenarios.

翻译：启发式调度规则（HDRs）被广泛认为是解决现实生产环境中动态作业车间调度问题（DJSSP）的有效方法。然而，其性能高度依赖于具体场景，通常需要专家进行定制。为此，遗传规划（GP）和基因表达式规划（GEP）已被广泛用于自动算法设计。尽管如此，这些方法常因搜索过程中的高度随机性和泛化能力有限而面临挑战，阻碍了训练好的调度规则在新场景或动态环境中的应用。近年来，大语言模型（LLMs）与进化算法的结合为提示工程和自动算法设计开辟了新途径。为增强LLMs在自动HDR设计方面的能力，本文提出一种新颖的种群自进化（SeEvo）方法，这是一种受人类专家自反思设计策略启发的通用搜索框架。SeEvo方法加速了搜索过程并增强了探索能力。实验结果表明，所提出的SeEvo方法在性能上优于GP、GEP、端到端深度强化学习方法以及文献中超过10种常见HDRs，尤其是在未见过的动态场景中。