Saved in:
Bibliographic Details
Main Authors: She, Buxin, Chen, Brian, Guo, Luanzheng, Li, Fangxing
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.10846
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913025275985920
author She, Buxin
Chen, Brian
Guo, Luanzheng
Li, Fangxing
author_facet She, Buxin
Chen, Brian
Guo, Luanzheng
Li, Fangxing
contents Power system simulation workflows remain expert-intensive. Engineers must translate study intents into code or API calls, execute analyses, and interpret outputs. To automate this workflow, this paper presents PFAgent, a tractable and self-evolving power-flow agent for interactive grid analysis. PFAgent integrates four key capabilities: i) a tractable and interactive architecture for intent parsing, knowledge retrieval, tool execution, and structured reporting; ii) a self-evolution mechanism combining verification-driven refinement and human-in-the-loop feedback; iii) an AI-assisted evaluation and debugging loop that leverages conversational context, generated code, and execution errors for iterative fixing; and iv) an evaluation framework covering task success, convergence validity, numerical consistency, and explanation quality. Verification on IEEE benchmark systems shows that PFAgent can automate case change, analyze voltage violations, perform N-1 contingency analysis, generate plots and concise summaries, and return reproducible results with transparent execution logs. The proposed framework highlights a shift from conventional simulation tools to interactive, tractable, and self-evolving agents for power system analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10846
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PFAgent: A Tractable and Self-Evolving Power-Flow Agent for Interactive Grid Analysis
She, Buxin
Chen, Brian
Guo, Luanzheng
Li, Fangxing
Systems and Control
Power system simulation workflows remain expert-intensive. Engineers must translate study intents into code or API calls, execute analyses, and interpret outputs. To automate this workflow, this paper presents PFAgent, a tractable and self-evolving power-flow agent for interactive grid analysis. PFAgent integrates four key capabilities: i) a tractable and interactive architecture for intent parsing, knowledge retrieval, tool execution, and structured reporting; ii) a self-evolution mechanism combining verification-driven refinement and human-in-the-loop feedback; iii) an AI-assisted evaluation and debugging loop that leverages conversational context, generated code, and execution errors for iterative fixing; and iv) an evaluation framework covering task success, convergence validity, numerical consistency, and explanation quality. Verification on IEEE benchmark systems shows that PFAgent can automate case change, analyze voltage violations, perform N-1 contingency analysis, generate plots and concise summaries, and return reproducible results with transparent execution logs. The proposed framework highlights a shift from conventional simulation tools to interactive, tractable, and self-evolving agents for power system analysis.
title PFAgent: A Tractable and Self-Evolving Power-Flow Agent for Interactive Grid Analysis
topic Systems and Control
url https://arxiv.org/abs/2604.10846