cs.AINov 16, 2026

Deploying a Control-Logic LLM Assistant in Air-Gapped Power Plants: Lessons in Source Authority and Bounded Retrieval

Authors: Yiwei Fu, Nicholas Gabriel

Organizations: GE Vernova Advanced Research Center Niskayuna, NY, USA

Abstract

Deploying Large Language Model (LLM) assistants in industrial operational technology environments poses constraints largely absent from cloud applications: site policies restrict engineering and operational data from leaving the plant, on-premises compute is limited, and incorrect causal attribution can mislead incident response. We report lessons from deploying a control-logic evidence layer that underpins a broader on-premises operator assistance system at two gas power plants. Two prototypes revealed where generative models added avoidable uncertainty and cost. The first used a Vision Language Model (VLM) to reconstruct control topology from PDF printouts routinely exchanged by engineers. Across the full 6,979-page document, extraction reached 0.51 connection precision and required 3.1 hours on 4xH200 GPUs; consultation with controls engineers then revealed a native structured export from the authoring system. The second used an LLM tool-calling agent to plan repeatedly over eight predefined graph operations. In a controlled benchmark of 40 template-generated questions, replacing this agent with explicit execution plans reduced mean token use by 20x and median latency by 3x, with identical retrieved node sets across repeated runs. The deployed design ingests the authoritative export into a versioned knowledge graph, executes bounded graph operations in fixed software, and confines the local LLM to fallback intent classification and evidence-grounded explanation. At one site, the graph contains 221K nodes across seven controllers. Our experience suggests a practical division of labor for high-consequence AI: LLMs interpret natural-language requests and explain results, while deterministic software constructs and retrieves technical evidence grounded in authoritative sources. Abstention, entity disambiguation, graph versioning, and read-only integration provide additional safeguards.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. PowerBench: A Benchmark for Agentic Retrieval and Reasoning in Power Systems

    Sep 28, 2026Xijing Wang, Yinsheng Yao, Jinru Ding +5LLM Agent EvaluationAI Agent Benchmarks

  2. Knowledge boundary probing and demand-guided intervention for LLM-based power system code generation

    May 29, 2026Hui Wu, Xiaoyang Wang, Zhong FanAutomated Program RepairCode Generation

  3. Knowledge Graphs as the Missing Data Layer for LLM-Based Industrial Asset Operations

    May 26, 2026Madhulatha Mandarapu, Sandeep KunkunuruLLM GroundingText-to-Cypher