DScheLLM: Enabling Dynamic Scheduling through a Fine-Tuned Dual-System Large language Model

TL;DR

This paper introduces DScheLLM, a novel dynamic scheduling method using a fine-tuned large language model with dual reasoning modes to adapt to disruptions in production environments.

Contribution

It presents a new framework that combines fast and slow reasoning with LLMs for dynamic scheduling, trained on datasets generated from exact schedules and fine-tuned with LoRA.

Findings

Fast mode efficiently generates high-quality schedules.

Slow mode produces solver-compatible decision inputs.

First application of LLMs to dynamic job shop scheduling.

Abstract

Production scheduling is highly susceptible to dynamic disruptions, such as variations in processing times, machine availability, and unexpected task insertions. Conventional approaches typically rely on event-specific models and explicit analytical formulations, which limits their adaptability and generalization across previously unseen disturbances. To overcome these limitations, this paper proposes DScheLLM, a dynamic scheduling approach that leverages fine-tuned large language models within a dual-system (fast-slow) reasoning architecture to address disturbances of different scales. A unified large language model-based framework is constructed to handle dynamic events, where training datasets for both fast and slow reasoning modes are generated using exact schedules obtained from an operations research solver. The Huawei OpenPangu Embedded-7B model is subsequently fine-tuned under the hybrid reasoning paradigms using LoRA. Experimental evaluations on standard job shop scheduling benchmarks demonstrate that the fast-thinking mode can efficiently generate high-quality schedules and the slow-thinking mode can produce solver-compatible and well-formatted decision inputs. To the best of our knowledge, this work represents one of the earliest studies applying large language models to job shop scheduling in dynamic environments, highlighting their considerable potential for intelligent and adaptive scheduling optimization.