Design of Equipment Control System Based on Large Language Models with Intelligent Validator Agent

Yu-Ching Lin; Chia-Chin Chen; Jyh-Horng Wu

doi:10.46604/ijeti.2026.15849

Authors

Yu-Ching Lin NCHCNational Center for High-Performance Computing, National Institutes of Applied Research, Taipei, Taiwan, ROC
Chia-Chin Chen National Center for High-Performance Computing, National Institutes of Applied Research, Taipei, Taiwan, ROC
Jyh-Horng Wu National Center for High-Performance Computing, National Institutes of Applied Research, Taipei, Taiwan, ROC

DOI:

https://doi.org/10.46604/ijeti.2026.15849

Keywords:

large language model (LLM), Retrieval-Augmented Generation (RAG), Mixture-of-Agents (MoA), Validator Agent, equipment control

Abstract

This study presents a comprehensive framework leveraging large language models (LLMs) for robust and accurate equipment control. The system integrates Retrieval-Augmented Generation (RAG) to provide LLMs with real-time contextual information retrieved from external knowledge sources. Furthermore, a Mixture-of-Agents (MoA) architecture is employed to harness the collective intelligence of multiple LLMs, enhancing the quality and reliability of generated control suggestions. The proposed intelligent Validator Agent, equipped with natural language processing capabilities and a feedback-correction mechanism, serves as the core component. The Validator Agent translates the LLM’s textual responses into actionable commands, validates them against real-time equipment status and predefined rules from a database, and corrects potential errors before execution. Performance evaluation demonstrates that although RAG and MoA improve accuracy, the Validator Agent’s correction loop remains essential. This research highlights the potential of combining LLMs with RAG, MoA, and intelligent agents to create highly accurate and reliable natural language-based equipment control systems.

References

N. Moenks, P. Penava, and R. Buettner, “A Systematic Literature Review of Large Language Model Applications in Industry,” IEEE Access, vol. 13, pp. 160010-160033, 2025.

X. Lin, W. Wang, Y. Li, S. Yang, F. Feng, Y. Wei, et al., “Data-Efficient Fine-Tuning for LLM-Based Recommendation,” Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 365-374, 2024.

Z. Zhang, Z. Shen, M. Yuan, F. Zhu, H. Ali, and G. Xiong, “RAGTraffic: Utilizing Retrieval-Augmented Generation for Intelligent Traffic Signal Control,” International Annual Conference on Complex Systems and Intelligent Science, pp. 728-735, 2024.

A. Onan, A. H. Nasution, and T. Celikten, “Toward Reliable Annotation in Low-Resource NLP: A Mixture of Agents Framework and Multi-LLM Benchmarking,” IEEE Access, vol. 13, pp. 211620-211644, 2025.

S. S. Bavirthi, D. P. Sreya, and T. Poojitha, “Comparative Analysis of Mixture-of-Agents Models for Natural Language Inference with ANLI Data,” Natural Language Processing Journal, vol. 11, article no. 100140, 2025.

D. Kaur, S. Uslu, M. Durresi, and A. Durresi, “LLM-Based Agents Utilized in a Trustworthy Artificial Conscience Model for Controlling AI in Medical Applications,” Proceedings of the 38th International Conference on Advanced Information Networking and Applications, vol. 3, pp. 198-209, 2024.

D. B. Acharya, K. Kuppan, and B. Divya, “Agentic AI: Autonomous Intelligence for Complex Goals—A Comprehensive Survey,” IEEE Access, vol. 13, pp. 18912-18936, 2025.

G. S. Sajja and S. R. Addula, “Automation Using Robots, Machine Learning, and Artificial Intelligence to Enhance Production and Quality,” Second International Conference Computational and Characterization Techniques in Engineering & Sciences, pp. 1-4, 2024.

S. R. Addula and A. K. Tyagi, “Future of Computer Vision and Industrial Robotics in Smart Manufacturing,” Artificial Intelligence‐Enabled Digital Twin for Smart Manufacturing, Hoboken, NJ: John Wiley & Sons, Inc., pp. 505-539, 2024.

Y. Xia, N. Jazdi, J. Zhang, C. Shah, and M. Weyrich, “Control Industrial Automation System with Large Language Model Agents,” IEEE 30th International Conference on Emerging Technologies and Factory Automation, pp. 1-8, 2025.

W. Huang, P. Abbeel, D. Pathak, and I. Mordatch, “Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents,” Proceedings of the 39th International Conference on Machine Learning, vol. 162, pp. 9118-9147, 2022.

J. Wang, E. Shi, H. Hu, C. Ma, Y. Liu, X. Wang, et al., “Large Language Models for Robotics: Opportunities, Challenges, and Perspectives,” Journal of Automation and Intelligence, vol. 4, no. 1, pp. 52-64, 2025.

H. Fan, X. Liu, J. Y. H. Fuh, W. F. Lu, and B. Li, “Embodied Intelligence in Manufacturing: Leveraging Large Language Models for Autonomous Industrial Robotics,” Journal of Intelligent Manufacturing, vol. 36, no. 2, pp. 1141-1157, 2025.

S. Paul, L. Zhang, Y. Shen, and H. Jin, “Enabling Device Control Planning Capabilities of Small Language Model,” IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 12066-12070, 2024.

Z. Wang and H. Qin, “Intelligent Industrial Production Process Automatic Regulation System Based on LLM Agents,” 5th International Conference on Artificial Intelligence and Electromechanical Automation, pp. 133-137, 2024.

D. Rivkin, F. Hogan, A. Feriani, A. Konar, A. Sigal, X. Liu, et al., “AIoT Smart Home via Autonomous LLM Agents,” IEEE Internet of Things Journal, vol. 12, no. 3, pp. 2458-2472, 2025.

C. Sun, S. Huang, and D. Pompili, “LLM-Based Multi-Agent Decision-Making: Challenges and Future Directions,” IEEE Robotics and Automation Letters, vol. 10, no. 6, pp. 5681-5688, 2025.

Z. Liu, R. Zeng, D. Wang, G. Peng, X. Liu, Q. Liu, et al., “Agents4PLC: Automating Closed-Loop PLC Code Generation and Verification in Industrial Control Systems Using LLM-Based Agents,” IEEE Transactions on Software Engineering, pp. 1-16, 2026.

B. Galitsky and A. Rybalov, “Neuro-Symbolic Verification for Preventing LLM Hallucinations in Process Control,” Processes, vol. 14, no. 2, article no. 322, 2026.

F. C. Ogenyi, C. N. Ugwu, and O. P. C. Ugwu, “Securing the Future: AI-Driven Cybersecurity in the Age of Autonomous IoT,” Frontiers in the Internet of Things, vol. 4, article no. 1658273, 2025.

S. Xu, Z. Yan, C. Dai, and F. Wu, “MEGA-RAG: A Retrieval-Augmented Generation Framework with Multi-Evidence Guided Answer Refinement for Mitigating Hallucinations of LLMs in Public Health,” Frontiers in Public Health, vol. 13, article no. 1635381, 2025.