Advances in Production Engineering & Management
Volume 20 | Number 4 | December 2025 | pp 491–506
https://doi.org/10.14743/apem2025.4.554
Using large language models (LLMs) to support simulation-based optimization in supply chain management
Wiśniewski, T.
ABSTRACT AND REFERENCES (PDF) |
FULL ARTICLE TEXT (PDF)
A B S T R A C T
The emergence of Artificial Intelligence (AI) in Supply Chain Management (SCM) heralds a transformative shift, breaking traditional barriers and unlocking new opportunities for optimization and efficiency. This study explores the impact of artificial intelligence, particularly large language models (LLMs), on simulation-based optimization applications in supply chain management. The novelty of LLMs lies in their ability to enhance both the technical and practical aspects of simulation-based optimization. On the technical side, LLMs can assist in constructing and fine-tuning optimization models by analyzing historical data, identifying patterns, and generating recommendations for optimal strategies. On the practical side, these models have the potential to simplify complex methodologies, making them more comprehensible and actionable for practitioners without extensive expertise in AI or advanced analytics. The article presents practical implications of LLMs in the form of a ChatGPT-based application, in which users express their supply chain challenges in natural language, and the model responds with tailored optimization strategies or simulation scenarios. The presented examples demonstrate how LLMs can automatically generate simulation models and support optimization processes in typical supply chain management scenarios. These results are preliminary and highlight both the potential of this approach and its current limitations, including occasional inaccuracies in the generated code.
A R T I C L E I N F O
Keywords • Supply chain management; Simulation-based optimization; Artificial intelligence; Large language models (LLMs); Generative AI; Conversational AI; ChatGPT; AI-driven decision-making
Corresponding author • Wiśniewski, T.
Article history • Received 3 July 2025, Revised 12 December 2025, Accepted 15 December 2025
Published on-line • 31 December 2025
E X P O R T C I T A T I O N
» RIS format (EndNote, ProCite, RefWorks, and most other reference management software)
» BibTeX (JabRef, BibDesk, and other BibTeX-specific software)
» Plain text
