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

The paper discusses the use of Large Language Models (LLMs) and Agentic AI systems in smart grids for tasks like forecasting, optimization, and control. It presents a design principle to ensure numerical results come from trusted tools and passes verification checks. The study compares an LLM-only baseline with solver-grounded versions in four case studies, showing significant improvements. A new evaluation framework is proposed.

What the Document Says

• The paper discusses the use of Large Language Models (LLMs) and Agentic AI systems in smart grids for tasks like forecasting, optimization, and control.
• It presents a design principle: a numerical result is reported only when it originates from a trusted tool and passes explicit verification.
• Four case studies are presented comparing an LLM-only baseline against its solver-grounded counterpart on identical data and metrics.
• The paper shows significant improvements in the case studies, with EVAgent reproducing the CVXPY optimum while reducing LLM-only unmet energy by 7.5-9.5x, and GridDebugAgent repairing 17/39 contingency cases while reducing total violations by 52.3%.
• A new four-group evaluation framework is proposed, spanning task utility, solver-grounded correctness, faithfulness and safe failure, and cost and latency.

Key Concepts Mentioned

• Large Language Models (LLMs)
• Agentic AI systems
• Smart grids
• Forecasting
• Optimization
• Control
• Design principle
• Case studies
• Evaluation framework

Claims Made by the Document

• The use of LLMs and Agentic AI systems in smart grids can improve performance significantly.
• The proposed design principle ensures numerical results are reliable.
• 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%.

Evidence Used

• The paper provides results from four case studies comparing LLM-only and solver-grounded versions.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

• What other tasks can these LLMs and Agentic AI systems be applied to in smart grids?
• How scalable are these systems when dealing with larger datasets or more complex scenarios?

Notes for Future Q&A

May include interpretation. Labeled where it does.

• The paper does not state the specific improvements for each of the four case studies individually.
• It is unclear what the baseline performance was before the introduction of the solver-grounded versions.

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.