LLMs can Schedule

TL;DR

This paper investigates the application of Large Language Models to the job shop scheduling problem, introducing a new dataset and methods that enable LLMs to perform competitively with specialized neural approaches.

Contribution

The paper presents the first supervised dataset for training LLMs on JSSP and proposes a sampling method to improve their scheduling performance.

Findings

LLMs can achieve performance comparable to other neural approaches in JSSP.

A new 120k supervised dataset for LLM training on scheduling tasks.

Sampling methods enhance LLM effectiveness in job scheduling.

Abstract

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.