Utilizing LLMs for Industrial Process Automation

Salim Fares

cs.SEFeb 26, 2026

Utilizing LLMs for Industrial Process Automation

Authors: Salim Fares

Organizations: University of Passau, Passau, Germany

Abstract

A growing number of publications address the best practices to use Large Language Models (LLMs) for software engineering in recent years. However, most of this work focuses on widely-used general purpose programming languages like Python due to their widespread usage training data. The utility of LLMs for software within the industrial process automation domain, with highly-specialized languages that are typically only used in proprietary contexts, remains underexplored. This research aims to utilize and integrate LLMs in the industrial development process, solving real-life programming tasks (e.g., generating a movement routine for a robotic arm) and accelerating the development cycles of manufacturing systems.

Figures & tables

	Accuracy
Task	German prompts	English prompts
Arguments Modification	$99.71\%$	$99.36\%$
Adding an Offset	$91.86\%$	$91.97\%$
Reversing	$77.27\%$	$83.72\%$

Table 1. The Accuracy for each task

Industrial Automation

See all 17 papers

IndustryCode: A Benchmark for Industry Code Generation
Apr 3, 2026Puyu Zeng, Zhaoxi Wang, Zhixu Duan +7Code Generation Code Generation Benchmarks
Shanghai Jiao Tong University, Shanghai, China · Alibaba Group, Hangzhou, China · Tsinghua University, Beijing, China
Pragmos: A Process Agentic Modeling System
Apr 30, 2026Pedro-Aarón Hernández-Ávalos, Luciano García-BañuelosAgentic Workflows Business Process Modeling
Tecnologico de Monterrey, Mexico
little m: An AI Agent for Industrial Process Optimization
Sep 15, 2026Yongchao Ye, Xinyu He, Dutliff Boshoff +2Large Language Model-Guided Optimization Multimodal Reasoning
Department of Data Science, City University of Hong Kong, Hong Kong SAR, China · Hong Kong Institute for Advanced Study, City University of Hong Kong

Apr 3, 2026J/K move · Enter open · S save

IndustryCode: A Benchmark for Industry Code Generation

Puyu Zeng, Zhaoxi Wang, Zhixu Duan, Liang Feng+6

Shanghai Jiao Tong University, Shanghai, China · Alibaba Group, Hangzhou, China · Tsinghua University, Beijing, China

Code Generation Code Generation Benchmarks Benchmark Design Multilingual Code Generation

Open paper AskPDF arXiv

Code generation and comprehension by Large Language Models (LLMs) have emerged as core drivers of industrial intelligence and decision optimization, finding widespread application in fields such as finance, automation, and aerospace. Although recent advancements have demonstrated the remarkable potential of LLMs in general code generation, existing benchmarks are mainly confined to single domains and languages. Consequently, they fail to effectively evaluate the generalization capabilities required for real-world industrial applications or to reflect the coding proficiency demanded by complex industrial scenarios. To bridge this gap, we introduce IndustryCode, the first comprehensive benchmark designed to span multiple industrial domains and programming languages. IndustryCode comprises 579 sub-problems derived from 125 primary industrial challenges, accompanied by rigorous problem descriptions and test cases. It covers a wide range of fields, including finance, automation, aerospace, and remote sensing-and incorporates diverse programming languages such as MATLAB, Python, C++, and Stata. In our evaluation, the top-performing model, Claude 4.5 Opus, achieved an overall accuracy of 68.1% on sub-problems and 42.5% main problems. The benchmark dataset and automated evaluation code will be made publicly available upon acceptance.

Abstract

Industrial Automation

Explore similar work

IndustryCode: A Benchmark for Industry Code Generation

Pragmos: A Process Agentic Modeling System

little m: An AI Agent for Industrial Process Optimization