LLM-Assisted Automatic Dispatching Rule Design for Dynamic Flexible Assembly Flow Shop Scheduling

2026-01-22

AI Summary

This work addresses the challenge of designing effective online dispatching rules for dynamic flexible assembly flow shop scheduling, where multi-stage temporal couplings and hierarchical supply constraints complicate decision-making. To this end, the authors propose the LLM4DRD framework, which formulates multi-stage processing and assembly decisions as a directed edge ordering problem on a heterogeneous graph. The approach integrates expert-knowledge-guided initialization with a dual large language model (LLM) collaboration mechanism—LLM-A for rule generation and LLM-S for schedule evaluation—enabling rule evolution driven by dynamic feature fitting and hybrid performance assessment. Evaluated on 20 real-world instances, the method reduces average tardiness by 3.17–12.39% compared to the state-of-the-art; across 480 heterogeneous scenarios, it outperforms the next-best approach by 11.10% in overall performance, demonstrating significantly enhanced generalization and robustness.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Mixed Discrete/Continuous Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Dynamic multi-product delivery environments demand rapid coordination of part completion and product-level kitting within hybrid processing and assembly systems to satisfy strict hierarchical supply constraints. The flexible assembly flow shop scheduling problem formally defines dependencies for multi-stage kitting, yet dynamic variants make designing integrated scheduling rules under multi-level time coupling highly challenging. Existing automated heuristic design methods, particularly genetic programming constrained to fixed terminal symbol sets, struggle to capture and leverage dynamic uncertainties and hierarchical dependency information under transient decision states. This study develops an LLM-assisted Dynamic Rule Design framework (LLM4DRD) that automatically evolves integrated online scheduling rules adapted to scheduling features. Firstly, multi-stage processing and assembly supply decisions are transformed into feasible directed edge orderings based on heterogeneous graph. Then, an elite knowledge guided initialization embeds advanced design expertise into initial rules to enhance initial quality. Additionally, a dual-expert mechanism is introduced in which LLM-A evolutionary code to generate candidate rules and LLM-S conducts scheduling evaluation, while dynamic feature-fitting rule evolution combined with hybrid evaluation enables continuous improvement and extracts adaptive rules with strong generalization capability. A series of experiments are conducted to validate the effectiveness of the method. The average tardiness of LLM4DRD is 3.17-12.39% higher than state-of-the-art methods in 20 practical instances used for training and testing, respectively. In 24 scenarios with different resource configurations, order loads, and disturbance levels totaling 480 instances, it achieves 11.10% higher performance than the second best competitor, exhibiting excellent robustness.

Problem

• dynamic scheduling
• flexible assembly flow shop
• hierarchical dependencies
• integrated dispatching rules
• multi-level time coupling

Innovation

• LLM-assisted scheduling
• dynamic rule design
• flexible assembly flow shop
• heterogeneous graph modeling
• dual-expert mechanism