# GridMind: LLMs-Powered Agents for Power System Analysis and Operations

arXiv: https://arxiv.org/abs/2509.02494 · HTML: https://mlsanity.com/paper/2509.02494/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use.
- Builds on 5 of its 34 references that are in the map.
- First posted on arXiv 2 Sep 2025.

## Placed in

- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

## Builds on (most cited first, 5 of 5)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion](https://mlsanity.com/paper/2310.11248/) (2023)
- [PowerModels.jl: An Open-Source Framework for Exploring Power Flow Formulations](https://mlsanity.com/paper/1711.01728/) (2017)
- [Real-Time Contingency Analysis with Corrective Transmission Switching - Part I: Methodology](https://mlsanity.com/paper/1604.05570/) (2016)

## Built on by (most cited first, 16 of 16)

- [X-GridAgent: An LLM-Powered Agentic AI System for Assisting Power Grid Analysis](https://mlsanity.com/paper/2512.20789/) (2025)
- [Knowledge boundary probing and demand-guided intervention for LLM-based power system code generation](https://mlsanity.com/paper/2605.31478/) (2026)
- [LLM Agents for Time-Series: A Survey](https://mlsanity.com/paper/2608.26226/) (2026)
- [Fault2Flow: An AlphaEvolve-Optimized Human-in-the-Loop Multi-Agent System for Fault-to-Workflow Automation](https://mlsanity.com/paper/2511.12916/) (2025)
- [ADKO: Agentic Decentralized Knowledge Optimization](https://mlsanity.com/paper/2605.07863/) (2026)
- [Grid-Orch: An LLM-Powered Orchestrator for Distribution Grid Simulation and Analytics](https://mlsanity.com/paper/2605.12728/) (2026)
- [Multi-Modal Agents for Power Distribution Defect Detection: An Evaluation of Foundation Models](https://mlsanity.com/paper/2606.12969/) (2026)
- [Power Systems Agent Benchmark: Executable Evaluation of AI Agents in Electric Power Engineering](https://mlsanity.com/paper/2606.20950/) (2026)
- [How Do Tool-Augmented LLM Agents Perform on Real-World Energy Analytics Tasks?](https://mlsanity.com/paper/2606.26346/) (2026)
- [LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and Applications](https://mlsanity.com/paper/2607.18147/) (2026)
- [Engineering Trustworthy Agentic AI for Critical Systems](https://mlsanity.com/paper/2607.18548/) (2026)
- [Binding Biometrics with AI Agent Identifiers for Delegation of Authority](https://mlsanity.com/paper/2608.04292/) (2026)
- [TwinGridShield: Consequence-Aware Runtime Authorization for LLM Grid-Agent Actions](https://mlsanity.com/paper/2608.15391/) (2026)
- [A-CPES: A Reference Framework for Agentic AI in Cyber-Physical Energy Systems](https://mlsanity.com/paper/2608.22672/) (2026)
- [A Governance-Aware Large Language Model Orchestrated Agentic Digital Twin for Transmission System Operator Control Room Decision Support](https://mlsanity.com/paper/2609.22476/) (2026)
- [Training Numerical Intelligence via Auto-Diagnosis and Skill Discovery](https://mlsanity.com/paper/2610.03872/) (2026)

## Abstract (arXiv)

The complexity of traditional power system analysis workflows presents significant barriers to efficient decision-making in modern electric grids. This paper presents GridMind, a multi-agent AI system that integrates Large Language Models (LLMs) with deterministic engineering solvers to enable conversational scientific computing for power system analysis. The system employs specialized agents coordinating AC Optimal Power Flow and N-1 contingency analysis through natural language interfaces while maintaining numerical precision via function calls. GridMind addresses workflow integration, knowledge accessibility, context preservation, and expert decision-support augmentation. Experimental evaluation on IEEE test cases demonstrates that the proposed agentic framework consistently delivers correct solutions across all tested language models, with smaller LLMs achieving comparable analytical accuracy with reduced computational latency. This work establishes agentic AI as a viable paradigm for scientific computing, demonstrating how conversational interfaces can enhance accessibility while preserving numerical rigor essential for critical engineering applications.