面向输电控制室的治理感知LLM智能体数字孪生
原标题：A Governance-Aware Large Language Model Orchestrated Agentic Digital Twin for Transmission System Operator Control Room Decision Support
AI 摘要
该论文提出一种面向输电系统运营商控制室的治理感知型LLM编排智能体数字孪生系统。LLM仅负责选择并参数化白名单分析工具，所有动作必须经过模型无法绕过的治理层，该层强制执行四条规则：仅执行白名单工具、不超步数预算、有副作用的动作需操作员明确批准、答案中每个数字均由后端结果渲染并附带单位变量时间。在希腊输电网络数字孪生的118任务基准上，主模型590次运行工具选择率达96.5%、任务成功率93.7%，四条规则无一例外成立；跨四个LLM共1416次运行规则全部成立，95%置信下界约99.8%；移除治理层后同一模型45次需批准运行全部未授权执行，仅39.2%答案含后端支持数字，执行开销为每请求12至16毫秒。
正文节选
[orcid=0000-0001-5249-5402] [orcid=0000-0002-2702-9140] [orcid=0000-0002-4942-1362] A Governance-Aware Large Language Model Orchestrated Agentic Digital Twin for Transmission System Operator Control Room Decision Support Abstract Transmission system operators face rising complexity from renewable integration, reduced inertia, and tighter security margins. Large language models offer natural-language decision support, but their hallucinations, uncontrolled tool use, and weak traceability conflict