TSGuard: Automated User-Centric Incident Diagnosis for AI Workloads in the Cloud
Proceedings of the ACM on Software Engineering · 2026-06-30 · 3 (FSE) · 253-276
DOI: 10.1145/3797149 ↗At a glance
Journal article in Proceedings of the ACM on Software Engineering, published online on 2026-06-30. Written by Yitao Yang and 5 co-authors. 75 references. The full text is freely available (open access, CC BY 4.0). Funded by: Research Grants Council, University Grants Committee, Chinese University of Hong Kong.
Abstract (original language)
AI workloads incur frequent failures and incidents from the underlying infrastructure. The current incident management workflow follows a provider-centric paradigm, where users report incidents to the infrastructure provider who then conducts troubleshooting. Due to the large number of incidents and the manual nature of the troubleshooting process, the provider often takes several days to resolve an incident, resulting in operational delays and productivity loss. To address these challenges, we present TSGuard, a user-centric multi-agent system that delivers immediate incident diagnosis to users who deploy the workloads. The core innovation of TSGuard is twofold: (1) constructing domain-specific knowledge bases by mining historical on-call experiences in the offline phase, and (2) mimicking human expert diagnosis via structured reasoning and iterative trial-and-error in the online phase. Evaluation using production incident records from Microsoft Azure demonstrates that TSGuard significantly outperforms state-of-the-art baselines, improving diagnostic accuracy by 19.8%. Furthermore, TSGuard reduces the average verification time by 63.4% compared to the sequential execution baseline.
Funding
- Research Grants Council, University Grants Committee
- Chinese University of Hong Kong
Cite
APA
Yang, Y., Deng, Y., Xiong, Y., Li, B., Xu, H., & Cheng, P. (2026). TSGuard: Automated User-Centric Incident Diagnosis for AI Workloads in the Cloud. Proceedings of the ACM on Software Engineering, 3(FSE), 253-276. https://doi.org/10.1145/3797149
Vancouver
Yang Y, Deng Y, Xiong Y, Li B, Xu H, Cheng P. TSGuard: Automated User-Centric Incident Diagnosis for AI Workloads in the Cloud. Proceedings of the ACM on Software Engineering. 2026;3(FSE):253-276. doi:10.1145/3797149
BibTeX
@article{Yang2026,
author = {Yang, Yitao and Deng, Yangtao and Xiong, Yifan and Li, Baochun and Xu, Hong and Cheng, Peng},
title = {TSGuard: Automated User-Centric Incident Diagnosis for AI Workloads in the Cloud},
journal = {Proceedings of the ACM on Software Engineering},
year = {2026},
volume = {3},
number = {FSE},
pages = {253--276},
doi = {10.1145/3797149}
}
EUVIMED