Fault2Flow: An AlphaEvolve-Optimized Human-in-the-Loop Multi-Agent System for Fault-to-Workflow Automation
Yafang Wang, Yangjie Tian, Xiaoyu Shen, Gaoyang Zhang, Jiaze Sun, He Zhang, Ruohua Xu, Feng Zhao
TL;DR
Fault2Flow tackles the fault diagnosis bottleneck in power grids by unifying unstructured regulatory logic and expert experiential knowledge into a verifiable, executable workflow. It introduces an AlphaEvolve-optimized, human-in-the-loop multi-agent system that (i) extracts regulatory logic into PASTA fault trees, (ii) incorporates expert verification, (iii) refines structure via AlphaEvolve, and (iv) synthesizes verified logic into executable n8n workflows. The approach is demonstrated on transformer fault diagnosis with a DL/T 722-2014 case, achieving 100% topological consistency and high semantic fidelity, and is quantified against four evaluation metrics showing superiority over end-to-end baselines while reducing computation. This work provides a reproducible pathway from domain fault analysis to operational automation, enabling scalable, maintainable, and auditable grid fault workflows with practical impact for grid reliability and safety. The framework’s demonstrated metrics include $TC>0.94$ and $E2ERC>0.72$, underscoring robust topology preservation and path coverage.
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.