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

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

• source_url: https://arxiv.org/abs/2607.18147
• source_type: paper
• platform: arxiv
• author: Daniela Rojas, Abdulwahab Albassam, Aidan G. Leung, Jett Ngo, Ryan Luo, Peter R....
• original_date: 2026-07-20
• added_date: 2026-07-22
• arxiv_id: 2607.18147
• arxiv_categories: eess.SY, cs.AI
• pdf_url: https://arxiv.org/pdf/2607.18147v1
• category: learning
• tags: smart-grid, agentic-ai, solver-grounded, tutorial, evaluation, arxiv
• quality_score: 5

摘要（中文）

智能电网场景下的 LLM/agent 教程：主张 solver-grounded 原则数值结果须来自可信工具并通过显式校验才可上报；覆盖 prompting 与 agent 架构积木，并在风电预测EV 调度潮流与事故诊断四案例对照 LLM-only 与 solver-grounded；提出任务效用求解正确性忠实与安全失败成本延迟四组评估框架收录理由：把模型编排 + 工具计算 + 校验门的分工写清楚，是垂直领域 agent 设计的高质量参考教程

Summary (English)

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.

One-liner

智能电网场景下的 LLM/agent 教程：主张 solver-grounded 原则数值结果须来自可信工具并通过显式校验才可上报...

原文 / 元数据抓取

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

作者: 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

原文链接: https://arxiv.org/abs/2607.18147

PDF: https://arxiv.org/pdf/2607.18147v1

发布时间: 2026-07-20

更新时间: 2026-07-20

分类: eess.SY, cs.AI

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.

Obsidian intake evidence excerpt

该内容文件由 AAIF content-fetcher 根据 active/high-score entry 与 OpenCLI arXiv 元数据补齐。

• entry_id: 6e16c57b
• title: LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and Applications
• source: https://arxiv.org/abs/2607.18147
• existing_summary_zh: 智能电网场景下的 LLM/agent 教程：主张 solver-grounded 原则数值结果须来自可信工具并通过显式校验才可上报；覆盖 prompting 与 agent 架构积木，并在风电预测EV 调度潮流与事故诊断四案例对照 LLM-only 与 solver-grounded；提出任务效用求解正确性忠实与安全失败成本延迟四组评估框架收录理由：把模型编排 + 工具计算 + 校验门的分工写清楚，是垂直领域 agent 设计的高质量参考教程