LLMs can Schedule
This addresses production optimization challenges for manufacturing/operations, but is incremental as it applies an existing AI paradigm (LLMs) to a new domain.
This paper tackles the job shop scheduling problem by exploring Large Language Models (LLMs) for the first time, creating a 120k supervised dataset for training and achieving performance comparable to existing neural approaches while proposing a sampling method to enhance effectiveness.
The job shop scheduling problem (JSSP) remains a significant hurdle in optimizing production processes. This challenge involves efficiently allocating jobs to a limited number of machines while minimizing factors like total processing time or job delays. While recent advancements in artificial intelligence have yielded promising solutions, such as reinforcement learning and graph neural networks, this paper explores the potential of Large Language Models (LLMs) for JSSP. We introduce the very first supervised 120k dataset specifically designed to train LLMs for JSSP. Surprisingly, our findings demonstrate that LLM-based scheduling can achieve performance comparable to other neural approaches. Furthermore, we propose a sampling method that enhances the effectiveness of LLMs in tackling JSSP.