Vendor-Aware Industrial Agents: RAG-Enhanced LLMs for Secure On-Premise PLC Code Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909992396783616 |
|---|---|
| author | Kersting, Joschka Rummel, Michael Benndorf, Gesa |
| author_facet | Kersting, Joschka Rummel, Michael Benndorf, Gesa |
| contents | Programmable Logic Controllers are operated by proprietary code dialects; this makes it challenging to train coding assistants. Current LLMs are trained on large code datasets and are capable of writing IEC 61131-3 compatible code out of the box, but they neither know specific function blocks, nor related project code. Moreover, companies like Mitsubishi Electric and their customers do not trust cloud providers. Hence, an own coding agent is the desired solution to cope with this. In this study, we present our work on a low-data domain coding assistant solution for industrial use. We show how we achieved high quality code generation without fine-tuning large models and by fine-tuning small local models for edge device usage. Our tool lets several AI models compete with each other, uses reasoning, corrects bugs automatically and checks code validity by compiling it directly in the chat interface. We support our approach with an extensive evaluation that comes with code compilation statistics and user ratings. We found that a Retrieval-Augmented Generation (RAG) supported coding assistant can work in low-data domains by using extensive prompt engineering and directed retrieval. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_09122 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Vendor-Aware Industrial Agents: RAG-Enhanced LLMs for Secure On-Premise PLC Code Generation Kersting, Joschka Rummel, Michael Benndorf, Gesa Software Engineering Artificial Intelligence Programmable Logic Controllers are operated by proprietary code dialects; this makes it challenging to train coding assistants. Current LLMs are trained on large code datasets and are capable of writing IEC 61131-3 compatible code out of the box, but they neither know specific function blocks, nor related project code. Moreover, companies like Mitsubishi Electric and their customers do not trust cloud providers. Hence, an own coding agent is the desired solution to cope with this. In this study, we present our work on a low-data domain coding assistant solution for industrial use. We show how we achieved high quality code generation without fine-tuning large models and by fine-tuning small local models for edge device usage. Our tool lets several AI models compete with each other, uses reasoning, corrects bugs automatically and checks code validity by compiling it directly in the chat interface. We support our approach with an extensive evaluation that comes with code compilation statistics and user ratings. We found that a Retrieval-Augmented Generation (RAG) supported coding assistant can work in low-data domains by using extensive prompt engineering and directed retrieval. |
| title | Vendor-Aware Industrial Agents: RAG-Enhanced LLMs for Secure On-Premise PLC Code Generation |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2511.09122 |