Pith. sign in

REVIEW 7 cited by

Autonomous Control Leveraging LLMs: An Agentic Framework for Next-Generation Industrial Automation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2507.07115 v1 pith:MIE4N62L submitted 2025-07-03 cs.AI cs.MAcs.SYeess.SY

classification cs.AIcs.MAcs.SYeess.SY
keywords controlllmsautomationframeworkagentagenticcasechemical
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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 both accuracy and latency. In Case Study 2, the same framework modulates dual-heater inputs on a laboratory TCLab platform (and its digital twin) to maintain a target average temperature under persistent asymmetric disturbances. Compared to classical PID control, our LLM-based controller attains similar performance, while ablation of the prompting loop reveals its critical role in handling nonlinear dynamics. We analyze key failure modes-such as instruction following lapses and coarse ODE approximations. Our results demonstrate that, with structured feedback and modular agents, LLMs can unify high-level symbolic planningand low-level continuous control, paving the way towards resilient, language-driven automation in chemical engineering.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. DART: Semantic Recoverability for Structured Tool Agents

    cs.AI 2026-05 unverdicted novelty 7.0 of 10

    DART is a modular runtime that certifies semantically recoverable boundaries for failed tool-agent instances and selects admissible restore points that preserve downstream commitments or blocks recovery.

  2. ADMITBench: A Safety-Governed Reference Framework for Evaluating the Admissibility of Industrial LLM Advisories

    cs.AI 2026-08 conditional novelty 6.0 of 10

    ADMITBench defines and implements a safety-governed evaluation framework that judges LLM industrial advisories at the level of the proposed action, using non-compensatory eligibility gates and versioned plant profiles.

  3. Safety-Gated Agentic Supervisory Control on a Coupled Distillation Benchmark: Regime Map, Auditable Gate, and Co-Design Findings

    eess.SY 2026-07 conditional novelty 6.0 of 10

    On a simulated distillation column, an ungated LLM supervisor beats linear MPC at off-nominal target re-planning but is ~10–16x worse at disturbance rejection; a forked-twin safety gate contains failures, yet 534 of 5...

  4. Towards an Intention Abstraction Layer for Autonomous Industrial Systems

    cs.AI 2026-07 conditional novelty 5.0 of 10

    A runtime middleware records autonomous agents' goals as structured, ontology-linked intentions and flags conflicts between them before execution, demonstrated on a two-agent production/energy scenario.

  5. Closed-Loop Control with Rule-Aligned Small Language Models and Multi-Agent Self-Correction

    cs.AI 2026-06 conditional novelty 5.0 of 10

    A GRPO-aligned Qwen2.5-1.5B multi-agent loop reaches 91.5% expert-action agreement and 95% in-range thermal regulation in randomized first-order simulations at 3.84 s mean latency.

  6. Large Language Models in Process Systems Engineering: Opportunities, Architectures, and Industrial Deployment Challenges

    eess.SY 2026-06 unverdicted novelty 4.0 of 10

    A systematic review of LLM applications in process systems engineering finds genuine utility for natural-language tasks but persistent challenges for real-time execution, constraint satisfaction, and safety guarantees.

  7. When control meets large language models: From words to dynamics

    eess.SY 2026-02 unverdicted novelty 3.0 of 10

    The paper proposes a bidirectional continuum between LLMs and control systems, covering LLM-assisted controller design, control-based LLM steering, and state-space modeling of LLMs.

Pith tools