Grid Agents：用于电力系统研究与并网评估的智能体框架
An Agentic Framework for Automated Power System Studies and Grid Connection Assessment
电网并网申请审查缺人手，这篇论文让智能体查法规、跑潮流计算，还把 519 个基准任务打包成套件，做能源 AI 的可以看看评测方法。
arXiv 论文提出 Grid Agents，将并网法规审查与电力系统网络研究合并在一套智能体系统中。其知识层 Grid Ontology 在 LegalBench-RAG 上领先，并位列 Enterprise RAG Challenge 和 ViDoRe V3 公开排行榜第一，引用监管证据的准确率高于通用编码智能体和检索流水线。工程层 Grid Studio 在整合 8 个已发表基准、共 519 个任务的电力系统测试套件上得分最高且速度最快。所有数字均由成熟求解器计算，工程师保留最终决策权，并可通过重放智能体的工具调用来验证过程。加入优化器后，强化学习训练包成本平均降低 33-67%。
An Agentic Framework for Automated Power System Studies and Grid Connection Assessment
Connecting new generation and demand to the grid depends on two scarce skills: checking applications against a large, changing body of regulation, and running the network studies that decide where and how a project connects. We present Grid Agents, an AI system that brings both together, and the methodology we use to evaluate it. The Grid Ontology is its knowledge system. It represents the regulation, standards and engineering knowledge that grid work depends on, makes it searchable, and evolves as the agents learn from use. Every answer drawn from it rests on evidence the agents cite. Grid Studio is an agent system specialised for power-system engineering. It works in its own engineering environment with domain tools and a study framework, draws on the Grid Ontology, and relies on established solvers for every number it reports. In both, engineers make the decisions. We bring eight published power-system benchmark families, previously scattered across separate papers, into one suite of 519 tasks, and we verify not only each answer but the work behind it, by replaying the agent's tool calls. The Grid Ontology cites the right regulatory evidence more often than a general coding agent or retrieval pipelines, leads on LegalBench-RAG and ranks first on the public leaderboards of the Enterprise RAG Challenge and ViDoRe V3. Grid Studio scores highest on the 519 power-system tasks and is the fastest of all the systems we compare, both by a statistically significant margin. With an optimiser in the loop, its reinforcement packages cost 33-67% less on average than those the agent designs alone.