Agents4PLC: Automating Closed-loop PLC Code Generation and Verification in Industrial Control Systems using LLM-based Agents

TL;DR

Agents4PLC tackles the critical need for automated, verifiable PLC code generation in industrial control systems by deploying an LLM-based multi-agent framework that orchestrates retrieval, planning, coding, debugging, and formal validation of ST code. It extends prior work with code-level verification, RAG-enabled knowledge access, and Chain-of-Thought–driven debugging, evaluated against a dedicated ST benchmark and real-world control scenarios. The results show superior automation, higher syntax correctness, and improved verifiability over existing approaches, demonstrating practical potential for safe, scalable PLC programming. The framework’s modularity and compatibility with tools like PLCverif and nuXMV position it as a flexible solution for industrial deployment and future expansion to additional PLC languages and standards.

Abstract

In industrial control systems, the generation and verification of Programmable Logic Controller (PLC) code are critical for ensuring operational efficiency and safety. While Large Language Models (LLMs) have made strides in automated code generation, they often fall short in providing correctness guarantees and specialized support for PLC programming. To address these challenges, this paper introduces Agents4PLC, a novel framework that not only automates PLC code generation but also includes code-level verification through an LLM-based multi-agent system. We first establish a comprehensive benchmark for verifiable PLC code generation area, transitioning from natural language requirements to human-written-verified formal specifications and reference PLC code. We further enhance our `agents' specifically for industrial control systems by incorporating Retrieval-Augmented Generation (RAG), advanced prompt engineering techniques, and Chain-of-Thought strategies. Evaluation against the benchmark demonstrates that Agents4PLC significantly outperforms previous methods, achieving superior results across a series of increasingly rigorous metrics. This research not only addresses the critical challenges in PLC programming but also highlights the potential of our framework to generate verifiable code applicable to real-world industrial applications.

Figures (6)

• Figure 1: Basic portrait of LLM-based agents
• Figure 2: Overview of Agents4PLC.
• Figure 3: An example of generating LED Control ST code with Agents4PLC.
• Figure 4: LED control with Agents4PLC.
• Figure 5: Motor triggering control with Agents4PLC.