LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and Applications
Daniela Rojas, Abdulwahab Albassam, Aidan G. Leung, Jett Ngo, Ryan Luo, Peter R. Quawas, Junpyung Kim, Kangkai Liang, Mansi Nanavati, Jonathan Mai, Meng-Chi Tsai, Yun-Tong Tsai, Yize Chen, Yuanyuan Shi
Why It Matters
What makes this one worth your time
This work is relevant for AI researchers and engineers interested in applying LLMs to technical domains like smart grids, offering a structured approach to ensure reliable and accurate outputs.
The paper proposes a solver-grounded design principle for using LLMs in smart grids, enhancing reliability and performance.
Summary
The paper explores the application of large language models (LLMs) and agentic AI systems in smart grids, focusing on forecasting, optimization, and control tasks. It introduces a solver-grounded design principle to ensure numerical results are reliable by using trusted tools and explicit verification. The study includes four case studies comparing LLM-only approaches with solver-grounded counterparts, demonstrating improvements in tasks like EV charging scheduling and contingency diagnosis. A four-group evaluation framework is proposed to assess task utility, correctness, faithfulness, and cost.
Key contributions
- Introduction of a solver-grounded design principle for LLMs in smart grids.
- Comparison of LLM-only and solver-grounded approaches across four case studies.
- Proposal of a four-group evaluation framework for assessing LLM-based systems.
Notable insights
- The solver-grounded design principle ensures that numerical results are only reported if they originate from a trusted tool and pass explicit verification.
- The paper proposes a four-group evaluation framework to comprehensively assess the performance of LLM-based systems in technical applications.
Possible limitations
- Not stated in the abstract
Abstract
arXiv:2607.18147v1 Announce Type: cross Abstract: Large language models (LLMs) and agentic AI systems have evolved from natural language tasks to using external tools to plan, retrieve, and act in technical domains. In smart grids, recent work applies agentic schemes to forecasting, optimization, and control, wrapping trusted solvers behind language interfaces and orchestrating multi-step workflows. The literature lacks a unified approach to designing and evaluating such systems. LLMs can produce numerically plausible yet physically infeasible outputs, evaluation protocols vary across tasks, and the boundary between what the model should and should not compute is implicit. This paper presents a solver-grounded design principle: a numerical result is reported only when it originates from a trusted tool and passes explicit verification. We review the building blocks of LLM and agentic AI systems for power systems: prompting strategies and agentic architectures. We instantiate the principle in four case studies: wind power forecasting, EV charging scheduling, power flow analysis, and contingency diagnosis, each comparing an LLM-only baseline against its solver-grounded counterpart on identical data and metrics. EVAgent reproduces the CVXPY optimum while reducing LLM-only unmet energy by 7.5-9.5x, and GridDebugAgent repairs 17/39 contingency cases while reducing total violations by 52.3%. We propose a four-group evaluation framework spanning task utility, solver-grounded correctness, faithfulness and safe failure, and cost and latency. A consistent division of labor emerges: the agentic system reliably orchestrates, retrieves, and explains, while trusted tools compute and a verification gate decides what is reported.