From Natural Language to Simulations: Applying GPT-3 Codex to Automate Simulation Modeling of Logistics Systems

TL;DR

This paper demonstrates how fine-tuned GPT-3 Codex can automatically generate functional simulation models of logistics systems from natural language descriptions, simplifying the development process for experts.

Contribution

It introduces a novel framework that applies GPT-3 Codex to automate simulation modeling of logistics systems from verbal descriptions, a first in this domain.

Findings

GPT-3 Codex can produce valid Python simulations of logistics systems.

The model understands domain-specific vocabulary and context.

Results suggest potential for workflow automation in simulation development.

Abstract

Our work is the first attempt to apply Natural Language Processing to automate the development of simulation models of systems vitally important for logistics. We demonstrated that the framework built on top of the fine-tuned GPT-3 Codex, a Transformer-based language model, could produce functionally valid simulations of queuing and inventory control systems given the verbal description. In conducted experiments, GPT-3 Codex demonstrated convincing expertise in Python as well as an understanding of the domain-specific vocabulary. As a result, the language model could produce simulations of a single-product inventory-control system and single-server queuing system given the domain-specific context, a detailed description of the process, and a list of variables with the corresponding values. The demonstrated results, along with the rapid improvement of language models, open the door for significant simplification of the workflow behind the simulation model development, which will allow experts to focus on the high-level consideration of the problem and holistic thinking.