Saved in:
Bibliographic Details
Main Authors: Wang, Yafang, Tian, Yangjie, Shen, Xiaoyu, Zhang, Gaoyang, Sun, Jiaze, Zhang, He, Xu, Ruohua, Zhao, Feng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.12916
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915621741002752
author Wang, Yafang
Tian, Yangjie
Shen, Xiaoyu
Zhang, Gaoyang
Sun, Jiaze
Zhang, He
Xu, Ruohua
Zhao, Feng
author_facet Wang, Yafang
Tian, Yangjie
Shen, Xiaoyu
Zhang, Gaoyang
Sun, Jiaze
Zhang, He
Xu, Ruohua
Zhao, Feng
contents Power grid fault diagnosis is a critical process hindered by its reliance on manual, error-prone methods. Technicians must manually extract reasoning logic from dense regulations and attempt to combine it with tacit expert knowledge, which is inefficient, error-prone, and lacks maintainability as ragulations are updated and experience evolves. While Large Language Models (LLMs) have shown promise in parsing unstructured text, no existing framework integrates these two disparate knowledge sources into a single, verified, and executable workflow. To bridge this gap, we propose Fault2Flow, an LLM-based multi-agent system. Fault2Flow systematically: (1) extracts and structures regulatory logic into PASTA-formatted fault trees; (2) integrates expert knowledge via a human-in-the-loop interface for verification; (3) optimizes the reasoning logic using a novel AlphaEvolve module; and (4) synthesizes the final, verified logic into an n8n-executable workflow. Experimental validation on transformer fault diagnosis datasets confirms 100\% topological consistency and high semantic fidelity. Fault2Flow establishes a reproducible path from fault analysis to operational automation, substantially reducing expert workload.
format Preprint
id arxiv_https___arxiv_org_abs_2511_12916
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fault2Flow: An AlphaEvolve-Optimized Human-in-the-Loop Multi-Agent System for Fault-to-Workflow Automation
Wang, Yafang
Tian, Yangjie
Shen, Xiaoyu
Zhang, Gaoyang
Sun, Jiaze
Zhang, He
Xu, Ruohua
Zhao, Feng
Artificial Intelligence
Power grid fault diagnosis is a critical process hindered by its reliance on manual, error-prone methods. Technicians must manually extract reasoning logic from dense regulations and attempt to combine it with tacit expert knowledge, which is inefficient, error-prone, and lacks maintainability as ragulations are updated and experience evolves. While Large Language Models (LLMs) have shown promise in parsing unstructured text, no existing framework integrates these two disparate knowledge sources into a single, verified, and executable workflow. To bridge this gap, we propose Fault2Flow, an LLM-based multi-agent system. Fault2Flow systematically: (1) extracts and structures regulatory logic into PASTA-formatted fault trees; (2) integrates expert knowledge via a human-in-the-loop interface for verification; (3) optimizes the reasoning logic using a novel AlphaEvolve module; and (4) synthesizes the final, verified logic into an n8n-executable workflow. Experimental validation on transformer fault diagnosis datasets confirms 100\% topological consistency and high semantic fidelity. Fault2Flow establishes a reproducible path from fault analysis to operational automation, substantially reducing expert workload.
title Fault2Flow: An AlphaEvolve-Optimized Human-in-the-Loop Multi-Agent System for Fault-to-Workflow Automation
topic Artificial Intelligence
url https://arxiv.org/abs/2511.12916