Fault2Flow: An AlphaEvolve-Optimized Human-in-the-Loop Multi-Agent System for Fault-to-Workflow Automation

TL;DR

Fault2Flow is a novel multi-agent system that leverages LLMs and human-in-the-loop verification to automate and optimize fault diagnosis workflows in power grids, improving accuracy and maintainability.

Contribution

It introduces a comprehensive framework combining fault tree extraction, expert verification, and AlphaEvolve optimization to automate fault-to-workflow conversion.

Findings

Achieved 100% topological consistency in fault diagnosis workflows.

High semantic fidelity in extracted and synthesized workflows.

Substantially reduces expert workload in fault diagnosis automation.

Abstract

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.