File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Cloud Infrastructure Management in the Age of AI Agents

TitleCloud Infrastructure Management in the Age of AI Agents
Authors
Yang, ZhenningBhatnagar, ArchitQiu, YimingMiao, TongyuanKon, Patrick Tser JernXiao, YunmingHuang, YiboCasado, MartinChen, Ang
Issue Date2025
Citation
Operating Systems Review ACM, 2025, v. 59, n. 2, p. 1-8 How to Cite?
DOI: http://dx.doi.org/10.1145/3759441.3759443
AbstractCloud infrastructure is the cornerstone of the modern IT industry. However, managing this infrastructure effectively requires considerable manual effort from the DevOps engineering team. We make a case for developing AI agents powered by large language models (LLMs) to automate cloud infrastructure management tasks. In a preliminary study, we investigate the potential for AI agents to use different cloud/user interfaces such as software development kits (SDK), command line interfaces (CLI), Infrastructure-as-Code (IaC) platforms, and web portals. We report takeaways on their effectiveness on different management tasks, and identify research challenges and potential solutions.
Persistent Identifierhttp://hdl.handle.net/10722/363057
ISSN
0163-5980
2023 SCImago Journal Rankings: 0.527

 

DC FieldValueLanguage
dc.contributor.authorYang, Zhenning-
dc.contributor.authorBhatnagar, Archit-
dc.contributor.authorQiu, Yiming-
dc.contributor.authorMiao, Tongyuan-
dc.contributor.authorKon, Patrick Tser Jern-
dc.contributor.authorXiao, Yunming-
dc.contributor.authorHuang, Yibo-
dc.contributor.authorCasado, Martin-
dc.contributor.authorChen, Ang-
dc.date.accessioned2025-10-10T07:44:19Z-
dc.date.available2025-10-10T07:44:19Z-
dc.date.issued2025-
dc.identifier.citationOperating Systems Review ACM, 2025, v. 59, n. 2, p. 1-8-
dc.identifier.issn0163-5980-
dc.identifier.urihttp://hdl.handle.net/10722/363057-
dc.description.abstractCloud infrastructure is the cornerstone of the modern IT industry. However, managing this infrastructure effectively requires considerable manual effort from the DevOps engineering team. We make a case for developing AI agents powered by large language models (LLMs) to automate cloud infrastructure management tasks. In a preliminary study, we investigate the potential for AI agents to use different cloud/user interfaces such as software development kits (SDK), command line interfaces (CLI), Infrastructure-as-Code (IaC) platforms, and web portals. We report takeaways on their effectiveness on different management tasks, and identify research challenges and potential solutions.-
dc.languageeng-
dc.relation.ispartofOperating Systems Review ACM-
dc.titleCloud Infrastructure Management in the Age of AI Agents-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1145/3759441.3759443-
dc.identifier.scopuseid_2-s2.0-105012730713-
dc.identifier.volume59-
dc.identifier.issue2-
dc.identifier.spage1-
dc.identifier.epage8-

Export via OAI-PMH Interface in XML Formats

OR

Export to Other Non-XML Formats