Hoang Tran, Huong Ha, Tri Dang, Jeffrey Chan, Hongyu Zhang · 2026 · arXiv
DOI: 10.48550/arXiv.2610.29185 · open-access PDF
El análisis de causas raíces (RCA) y la predicción de mitigación son esenciales para la gestión de incidentes, permitiendo la identificación de las causas subyacentes de fallos y asegurando la fiabilidad de los sistemas basados en la nube complejos. Con el aumento del volumen de incidentes y la complejidad del sistema, los informes de incidentes se han convertido en un recurso valioso para estas tareas. Los estudios recientes han mostrado resultados prometedores utilizando modelos de idiomas grandes (LLM) para predecir causas raíces y acciones de mitigación a partir de descripciones textuales en los informes de incidentes.
Machine translation (Meta M2M100); the English original follows.
Root cause analysis (RCA) and mitigation prediction are essential for incident management, enabling the identification of underlying causes of failures and ensuring the reliability of complex cloud-based systems. With rising incident volume and system complexity, incident reports have become a valuable resource for these tasks. Recent studies have shown promising results using Large Language Models (LLMs) to predict root causes and mitigation actions from textual descriptions in incident reports. Despite these advances, further progress is hindered by the lack of publicly available datasets; e
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29185, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange