We are delighted to introduce X-GridAgent 1.0, a large language model (LLM)-powered agentic AI system designed to automate complex power system analysis through natural language queries. The system integrates domain-specific tools and specialized databases under a three-layer hierarchical architecture comprising planning, coordination, and action layers. X-GridAgent 1.0 enables users to perform a wide range of professional power system analyses, including power flow analysis, contingency analysis, optimal power flow (OPF), short-circuit calculation, and topology search, among others. It also features effective long-term & short-term memory management, as well as information retrieval from large-scale grid databases and documentation.
Featured Publications:
[1] Yihan Wen, Xin Chen, "X-GridAgent: An LLM-Powered Agentic AI System for Assisting Power Grid Analysis", arXiv:2512.20789, 2025.
Key features of X-GridAgent
The three-layer hierarchical architecture of X-GridAgent