LLMs can Schedule

Henrik Abgaryan, Ararat Harutyunyan, Tristan Cazenave
8/13/2024
cs.AI

No official code found. Best implementation: starjob42/datasetjsp (12 stars, last commit 2025-06-12).

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.

View on arXivView PDF

Code Implementations(1)

starjob42/datasetjspCommunity100%

Dataset2024

122PythonJun 5, 20241 years ago

Similar Papers

Deep reinforcement learning for machine scheduling: Methodology, the state-of-the-art, and future directions

87% match2023

Beyond Training: Optimizing Reinforcement Learning Based Job Shop Scheduling Through Adaptive Action Sampling

86% match2024

A Production Scheduling Framework for Reinforcement Learning Under Real-World Constraints

86% match1 repo532025

Solving the flexible job-shop scheduling problem through an enhanced deep reinforcement learning approach

86% match2023

Learning to Solve Job Shop Scheduling under Uncertainty

85% match1 repo822024

Policy-Based Deep Reinforcement Learning Hyperheuristics for Job-Shop Scheduling Problems

85% match2026

Cite this paper

@article{abgaryan2024llms,
  title  = {LLMs can Schedule},
  author = {Henrik Abgaryan and Ararat Harutyunyan and Tristan Cazenave},
  year   = {2024},
  eprint = {2408.06993},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2408.06993v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2408.06993.svg)](https://codeofpaper.com/paper/2408.06993)

Discussion