Autonomous Control Leveraging LLMs: An Agentic Framework for Next-Generation Industrial Automation
Javal Vyas, Mehmet Mercangoz

TL;DR
This paper presents a novel agentic framework using large language models for integrated fault recovery planning and process control in chemical automation, demonstrating high success rates and comparable performance to classical methods.
Contribution
It introduces a unified LLM-based architecture combining symbolic fault planning and continuous control within a finite state machine framework, advancing resilient automation.
Findings
100% valid-path success in FSM case studies
LLM-based controller matches PID performance
Structured feedback improves handling of nonlinear dynamics
Abstract
The increasing complexity of modern chemical processes, coupled with workforce shortages and intricate fault scenarios, demands novel automation paradigms that blend symbolic reasoning with adaptive control. In this work, we introduce a unified agentic framework that leverages large language models (LLMs) for both discrete fault-recovery planning and continuous process control within a single architecture. We adopt Finite State Machines (FSMs) as interpretable operating envelopes: an LLM-driven planning agent proposes recovery sequences through the FSM, a Simulation Agent executes and checks each transition, and a Validator-Reprompting loop iteratively refines invalid plans. In Case Study 1, across 180 randomly generated FSMs of varying sizes (4-25 states, 4-300 transitions), GPT-4o and GPT-4o-mini achieve 100% valid-path success within five reprompts-outperforming open-source LLMs in…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsFormal Methods in Verification · Machine Learning and Algorithms · Process Optimization and Integration
