发表机构
Department of Electrical and Computer Engineering, University of California San Diego; Department of Electrical and Computer Engineering, University of Alberta（加州大学圣迭戈分校电气与计算机工程系; 阿尔伯塔大学电气与计算机工程系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究智能电网中LLMs和智能AI系统，提出基于求解器的设计原则，通过提示策略等构建模块及四个案例研究实例化该原则，比较不同方案，还提出四组评估框架，明确了各部分分工。
AI 中文摘要
大语言模型（LLMs）和智能AI系统已从自然语言任务发展到在技术领域中使用外部工具进行规划、检索和行动。在智能电网中，近期工作将智能方案应用于预测、优化和控制，在语言接口后包装可信求解器并编排多步工作流程。文献中缺乏设计和评估此类系统的统一方法。本文提出基于求解器的设计原则：仅当数值结果源自可信工具并通过显式验证时才报告。回顾了用于电力系统的LLM和智能AI系统的构建模块：提示策略和智能架构。通过四个案例研究实例化该原则，比较了仅使用LLM的基线与其基于求解器的对应方案。提出了一个涵盖任务效用、基于求解器的正确性、忠实性和安全失败以及成本和延迟的四组评估框架。
英文摘要
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.
Comments28 pages, 11 figures, 6 tables; plus supplementary material. Review/tutorial article
