# Leveraging LLM Agents and Digital Twins for Fault Handling in Process Plants

arXiv: https://arxiv.org/abs/2505.02076 · HTML: https://mlsanity.com/paper/2505.02076/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 4 May 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Towards autonomous system: flexible modular production system enhanced with large language model agents](https://mlsanity.com/paper/2304.14721/) (2023)
- [Agents4PLC: Automating Closed-loop PLC Code Generation and Verification in Industrial Control Systems using LLM-based Agents](https://mlsanity.com/paper/2410.14209/) (2024)
- [LLM4PLC: Harnessing Large Language Models for Verifiable Programming of PLCs in Industrial Control Systems](https://mlsanity.com/paper/2401.05443/) (2024)
- [Autonomous Industrial Control using an Agentic Framework with Large Language Models](https://mlsanity.com/paper/2411.05904/) (2024)
- [Pre-Trained Large Language Models for Industrial Control](https://mlsanity.com/paper/2308.03028/) (2023)
- [Explainable Predictive Maintenance: A Survey of Current Methods, Challenges and Opportunities](https://mlsanity.com/paper/2401.07871/) (2024)
- [Representing Timed Automata and Timing Anomalies of Cyber-Physical Production Systems in Knowledge Graphs](https://mlsanity.com/paper/2308.13433/) (2023)
- [Integrating Ontology Design with the CRISP-DM in the context of Cyber-Physical Systems Maintenance](https://mlsanity.com/paper/2407.06930/) (2024)

## Built on by (most cited first, 9 of 9)

- [Autonomous Control Leveraging LLMs: An Agentic Framework for Next-Generation Industrial Automation](https://mlsanity.com/paper/2507.07115/) (2025)
- [From Detection to Action: Using LLM Agents for Fault-Tolerant Control](https://mlsanity.com/paper/2606.28011/) (2026)
- [Sensory-Motor Control with Large Language Models via Iterative Policy Refinement](https://mlsanity.com/paper/2506.04867/) (2025)
- [FacProcessTwin: An LLM-Based System for Process Twin Development](https://mlsanity.com/paper/2606.17666/) (2026)
- [Automating Cause-Effect Specification with Knowledge Graphs and Large Language Models](https://mlsanity.com/paper/2606.31614/) (2026)
- [A Tutorial on Autonomous Fault-Tolerant Control Using Knowledge-Grounded LLM Agents](https://mlsanity.com/paper/2606.31635/) (2026)
- [Closed-Loop Control with Rule-Aligned Small Language Models and Multi-Agent Self-Correction](https://mlsanity.com/paper/2607.09713/) (2026)
- [Safety-Gated Agentic Supervisory Control on a Coupled Distillation Benchmark: Regime Map, Auditable Gate, and Co-Design Findings](https://mlsanity.com/paper/2607.27849/) (2026)
- [ADMITBench: A Safety-Governed Reference Framework for Evaluating the Admissibility of Industrial LLM Advisories](https://mlsanity.com/paper/2608.03866/) (2026)

## Abstract (arXiv)

Advances in Automation and Artificial Intelligence continue to enhance the autonomy of process plants in handling various operational scenarios. However, certain tasks, such as fault handling, remain challenging, as they rely heavily on human expertise. This highlights the need for systematic, knowledge-based methods. To address this gap, we propose a methodological framework that integrates Large Language Model (LLM) agents with a Digital Twin environment. The LLM agents continuously interpret system states and initiate control actions, including responses to unexpected faults, with the goal of returning the system to normal operation. In this context, the Digital Twin acts both as a structured repository of plant-specific engineering knowledge for agent prompting and as a simulation platform for the systematic validation and verification of the generated corrective control actions. The evaluation using a mixing module of a process plant demonstrates that the proposed framework is capable not only of autonomously controlling the mixing module, but also of generating effective corrective actions to mitigate a pipe clogging with only a few reprompts.