LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and Applications

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: 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
• Venue: arXiv: eess.SY
• Published: 2026-07-20
• Collected: 2026-07-21
• URL: http://arxiv.org/abs/2607.18147v1
• PDF: https://arxiv.org/pdf/2607.18147v1
• DOI: UNKNOWN

Plain-Language Brief

This paper discusses how large language models (LLMs) and agentic AI systems are being used in smart grids for tasks like forecasting, optimization, and control. The authors present a design principle called the solver-grounded approach to ensure the outputs from these systems are numerically accurate and physically feasible. They review various prompting strategies and agentic architectures used in power systems and provide four case studies demonstrating the effectiveness of this approach. For instance, EVAgent reproduces the optimal solution for EV charging scheduling while reducing energy shortages by a significant margin compared to an LLM-only baseline.

What the Document Says

• LLMs and agentic AI systems are used in smart grids for tasks like forecasting, optimization, and control.
• The authors propose the solver-grounded design principle: a numerical result is reported only when it originates from a trusted tool and passes explicit verification.
• They review prompting strategies and agentic architectures used in power systems.
• Four case studies are provided demonstrating the effectiveness of the solver-grounded approach.
• EVAgent reproduces the CVXPY optimum while reducing LLM-only unmet energy by 7.5-9.5x.
• GridDebugAgent repairs 17/39 contingency cases while reducing total violations by 52.3%.

Key Concepts Mentioned

• Large Language Models (LLMs)
• agentic AI systems
• smart grids
• forecasting
• optimization
• control
• solver-grounded design principle

Claims Made by the Document

• Solver-grounded design principle improves the accuracy of numerical results.
• EVAgent reduces LLM-only unmet energy significantly.

Evidence Used

• The paper discusses the solver-grounded design principle
• The case studies demonstrate the effectiveness of the solver-grounded approach
• The numbers provided for EVAgent's performance indicate a significant reduction in unmet energy

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.