Research

Paper

AI LLM February 24, 2026

Grid-Mind: An LLM-Orchestrated Multi-Fidelity Agent for Automated Connection Impact Assessment

Authors

Mohamed Shamseldein

Abstract

Large language models (LLMs) have demonstrated remarkable tool-use capabilities, yet their application to power system operations remains largely unexplored. This paper presents Grid-Mind, a domain-specific LLM agent that interprets natural-language interconnection requests and autonomously orchestrates multi-fidelity power system simulations. The LLM-first architecture positions the language model as the central decision-making entity, employing an eleven-tool registry to execute Connection Impact Assessment (CIA) studies spanning steadystate power flow, N-1 contingency analysis, transient stability, and electromagnetic transient screening. A violation inspector grounds every decision in quantitative simulation outputs, while a three-layer anti-hallucination defence mitigates numerical fabrication risk through forced capacity-tool routing and post-response grounding validation. A prompt-level self-correction mechanism extracts distilled lessons from agent failures, yielding progressive accuracy improvements without model retraining. End-to-end evaluation on 50 IEEE 118-bus scenarios (DeepSeek-V3, 2026-02-23) achieved 84.0% tool-selection accuracy and 100% parsing accuracy. A separate 56-scenario self-correction suite passed 49 of 56 cases (87.5%) with a mean score of 89.3. These results establish a reproducible baseline for continued refinement while maintaining auditable, simulation-grounded decision support.

Metadata

arXiv ID: 2602.20683
Provider: ARXIV
Primary Category: eess.SY
Published: 2026-02-24
Fetched: 2026-02-25 06:05

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.20683v1</id>\n    <title>Grid-Mind: An LLM-Orchestrated Multi-Fidelity Agent for Automated Connection Impact Assessment</title>\n    <updated>2026-02-24T08:40:54Z</updated>\n    <link href='https://arxiv.org/abs/2602.20683v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.20683v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Large language models (LLMs) have demonstrated remarkable tool-use capabilities, yet their application to power system operations remains largely unexplored. This paper presents Grid-Mind, a domain-specific LLM agent that interprets natural-language interconnection requests and autonomously orchestrates multi-fidelity power system simulations. The LLM-first architecture positions the language model as the central decision-making entity, employing an eleven-tool registry to execute Connection Impact Assessment (CIA) studies spanning steadystate power flow, N-1 contingency analysis, transient stability, and electromagnetic transient screening. A violation inspector grounds every decision in quantitative simulation outputs, while a three-layer anti-hallucination defence mitigates numerical fabrication risk through forced capacity-tool routing and post-response grounding validation. A prompt-level self-correction mechanism extracts distilled lessons from agent failures, yielding progressive accuracy improvements without model retraining. End-to-end evaluation on 50 IEEE 118-bus scenarios (DeepSeek-V3, 2026-02-23) achieved 84.0% tool-selection accuracy and 100% parsing accuracy. A separate 56-scenario self-correction suite passed 49 of 56 cases (87.5%) with a mean score of 89.3. These results establish a reproducible baseline for continued refinement while maintaining auditable, simulation-grounded decision support.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='eess.SY'/>\n    <published>2026-02-24T08:40:54Z</published>\n    <arxiv:primary_category term='eess.SY'/>\n    <author>\n      <name>Mohamed Shamseldein</name>\n    </author>\n  </entry>"
}