An LLM-powered MILP modelling engine for workforce scheduling guided by expert knowledge
Preprint
Abstract
Formulating mathematical models from real-world decision problems is a core task in Operational Research, yet it typically requires considerable human expertise and effort, limiting practical application. Recent advances in large language models (LLMs) have sparked interest in automating this process from natural language descriptions. However, challenges including limited modelling expertise, dependence on large-scale training data, and hallucination affect the reliable application of LLMs in optimisation modelling. To address these challenges, we propose SMILO, an expert-knowledge-driven framework that integrates optimisation modelling expertise with LLMs to generate mixed-integer linear programming models. SMILO uses a three-stage architecture built on reusable modelling graphs and associated resources: identifying relevant modelling components, extracting instance-specific information using LLMs, and constructing models through expert-defined templates. This modular architecture separates information extraction from formula generation, enhancing modelling accuracy, transparency, and reproducibility. We demonstrate the implementation of our modelling framework using workforce scheduling problems spanning manufacturing, logistic, and service operations as illustrative cases. Experiments show that SMILO consistently generates correct models in 90% of test instances across five trials, outperforming one-step LLM baselines by at least 35%. This work offers a generalisable paradigm for integrating LLMs with expert knowledge across diverse decision-making contexts, advancing automation in optimisation modelling.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Constructing modified variable neighborhood search approaches to solve a nurse scheduling problemInternational Journal of Production Research, 2024
- Generative artificial intelligence in supply chain and operations management: a capability-based framework for analysis and implementationInternational Journal of Production Research, 2024
- ChatGPT and generative artificial intelligence: an exploratory study of key benefits and challenges in operations and supply chain managementInternational Journal of Production Research, 2023
- From natural language to simulations: applying AI to automate simulation modelling of logistics systemsInternational Journal of Production Research, 2023
- Food inspector scheduling with outcome and daily-schedule effectsInternational Journal of Production Research, 2023
- Towards knowledge graph reasoning for supply chain risk management using graph neural networksInternational Journal of Production Research, 2022
- A co-availability scheduling model for coordinating multi-disciplinary care teamsInternational Journal of Production Research, 2015
- Personnel scheduling: A literature reviewEuropean Journal of Operational Research, 2013
- Survey, Categorization, and Comparison of Recent Tour Scheduling LiteratureAnnals of Operations Research, 2004
- Staff scheduling at the United States Postal ServiceComputers & Operations Research, 2003