Starjob: Dataset for LLM-Driven Job Shop Scheduling

2025-02-26

AI Summary

This work investigates the feasibility of leveraging large language models (LLMs) to solve the Job-Shop Scheduling Problem (JSSP). Addressing the critical bottleneck—lack of LLM-adapted training data and suitable paradigms for JSSP—we introduce StarJob, the first large-scale supervised dataset comprising 130,000 JSSP instances, and propose a novel end-to-end paradigm wherein LLMs directly generate scheduling actions. Using LoRA fine-tuning and 4-bit quantization on LLaMA-8B, we implement instruction-tuned JSSP instance encoding and serialized decision generation. Experiments demonstrate that our approach outperforms the state-of-the-art neural method L2D by 15.36% on the DMU benchmark and 7.85% on the Taillard benchmark, while significantly surpassing classical heuristic rules. These results validate the modeling capability and practical utility of LLMs in combinatorial optimization tasks.

Technology Category

• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Large Language Models (LLMs) have shown remarkable capabilities across various domains, but their potential for solving combinatorial optimization problems remains largely unexplored. In this paper, we investigate the applicability of LLMs to the Job Shop Scheduling Problem (JSSP), a classic challenge in combinatorial optimization that requires efficient job allocation to machines to minimize makespan. To this end, we introduce Starjob, the first supervised dataset for JSSP, comprising 130k instances specifically designed for training LLMs. Leveraging this dataset, we fine-tune the LLaMA 8B 4-bit quantized model with the LoRA method to develop an end-to-end scheduling approach. Our evaluation on standard benchmarks demonstrates that the proposed LLM-based method not only surpasses traditional Priority Dispatching Rules (PDRs) but also achieves notable improvements over state-of-the-art neural approaches like L2D, with an average improvement of 15.36% on DMU and 7.85% on Taillard benchmarks. These results highlight the untapped potential of LLMs in tackling combinatorial optimization problems, paving the way for future advancements in this area.

Problem

• Explores LLMs for solving Job Shop Scheduling Problem.
• Introduces Starjob dataset for training LLMs on JSSP.
• Demonstrates LLM-based method outperforms traditional scheduling approaches.

Innovation

• Introduces Starjob dataset for JSSP training
• Fine-tunes LLaMA 8B model using LoRA method
• Achieves significant improvements over traditional methods