{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:14:39Z","timestamp":1777421679487,"version":"3.51.4"},"reference-count":45,"publisher":"Association for Computing Machinery (ACM)","issue":"1","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGOPS Oper. Syst. Rev."],"published-print":{"date-parts":[[2025,8,4]]},"abstract":"<jats:p>Cloud 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.<\/jats:p>","DOI":"10.1145\/3759441.3759443","type":"journal-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T14:43:44Z","timestamp":1754491424000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Cloud Infrastructure Management in the Age of AI Agents"],"prefix":"10.1145","volume":"59","author":[{"given":"Zhenning","family":"Yang","sequence":"first","affiliation":[{"name":"University of Michigan, MI, USA"}]},{"given":"Archit","family":"Bhatnagar","sequence":"additional","affiliation":[{"name":"University of Michigan, MI, USA"}]},{"given":"Yiming","family":"Qiu","sequence":"additional","affiliation":[{"name":"University of Michigan, MI, USA"}]},{"given":"Tongyuan","family":"Miao","sequence":"additional","affiliation":[{"name":"University of Michigan, MI, USA"}]},{"given":"Patrick","family":"Tser Jern Kon","sequence":"additional","affiliation":[{"name":"University of Michigan, MI, USA"}]},{"given":"Yunming","family":"Xiao","sequence":"additional","affiliation":[{"name":"University of Michigan, MI, USA"}]},{"given":"Yibo","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Michigan, MI, USA"}]},{"given":"Martin","family":"Casado","sequence":"additional","affiliation":[{"name":"Andreessen Horowitz"}]},{"given":"Ang","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Michigan, MI, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,8,6]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"facts & trends for","year":"2023","unstructured":"26 cloud computing statistics, facts & trends for 2023. https:\/\/www.cl oudwards.net\/cloud-computing-statistics\/#Sources."},{"key":"e_1_2_1_2_1","unstructured":"Amazon Q in AWS services. https:\/\/aws.amazon.com\/q\/."},{"key":"e_1_2_1_3_1","unstructured":"AWS CloudFormation. https:\/\/aws.amazon.com\/cloudformation\/."},{"key":"e_1_2_1_4_1","unstructured":"Crossplane: Cloud-native framework for platform engineering. https: \/\/www.crossplane.io\/."},{"key":"e_1_2_1_5_1","unstructured":"Gemini for Google Cloud. https:\/\/cloud.google.com\/products\/gemini."},{"key":"e_1_2_1_6_1","unstructured":"LangChain build context-aware reasoning applications. https:\/\/www. langchain.com\/."},{"key":"e_1_2_1_7_1","unstructured":"Microsoft copilot in Azure. https:\/\/azure.microsoft.com\/en-us\/produ cts\/copilot."},{"key":"e_1_2_1_8_1","unstructured":"OpenTofu: The open source infrastructure as code tool. https:\/\/open tofu.org\/."},{"key":"e_1_2_1_9_1","unstructured":"Pulumi: Infrastructure as code in any programming language. https: \/\/www.pulumi.com\/."},{"key":"e_1_2_1_10_1","unstructured":"Terraform by Hashicorp. https:\/\/www.terraform.io\/."},{"key":"e_1_2_1_11_1","unstructured":"What is infrastructure as code (IaC). https:\/\/learn.microsoft.com\/enus\/ devops\/deliver\/what-is-infrastructure-as-code."},{"key":"e_1_2_1_12_1","volume":"202","author":"Alonso Juncal","unstructured":"Juncal Alonso, Leire Orue-Echevarria, Valentina Casola, Ana Isabel Torre, Maider Huarte, Eneko Osaba, and Jesus L. Lobo. Understanding the challenges and novel architectural models of multi-cloud native applications - a systematic literature review. J. Cloud Comput., 2023.","journal-title":"J. Cloud Comput."},{"key":"e_1_2_1_13_1","volume-title":"Openai gym","author":"Brockman Greg","year":"2016","unstructured":"Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, and Wojciech Zaremba. Openai gym, 2016."},{"key":"e_1_2_1_14_1","volume-title":"Aiopslab: A holistic framework to evaluate ai agents for enabling autonomous clouds","author":"Chen Yinfang","year":"2024","unstructured":"Yinfang Chen, Manish Shetty, Gagan Somashekar, Minghua Ma, Yogesh Simmhan, Jonathan Mace, Chetan Bansal, Rujia Wang, and Saravan Rajmohan. Aiopslab: A holistic framework to evaluate ai agents for enabling autonomous clouds, 2024."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629553"},{"key":"e_1_2_1_16_1","volume-title":"Agentpoison: Red-teaming llm agents via poisoning memory or knowledge bases","author":"Chen Zhaorun","year":"2024","unstructured":"Zhaorun Chen, Zhen Xiang, Chaowei Xiao, Dawn Song, and Bo Li. Agentpoison: Red-teaming llm agents via poisoning memory or knowledge bases, 2024."},{"key":"e_1_2_1_17_1","volume-title":"Tom Marty, L\u00e9o Boisvert, Megh Thakkar, Quentin Cappart, David Vazquez, Nicolas Chapados, and Alexandre Lacoste. Workarena: How capable are web agents at solving common knowledge work tasks?","author":"Drouin Alexandre","year":"2024","unstructured":"Alexandre Drouin, Maxime Gasse, Massimo Caccia, Issam H. Laradji, Manuel Del Verme, Tom Marty, L\u00e9o Boisvert, Megh Thakkar, Quentin Cappart, David Vazquez, Nicolas Chapados, and Alexandre Lacoste. Workarena: How capable are web agents at solving common knowledge work tasks?, 2024."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-15035-8_103"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.67"},{"key":"e_1_2_1_20_1","volume-title":"The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Jern Kon Patrick Tser","year":"2024","unstructured":"Patrick Tser Jern Kon, Jiachen Liu, Yiming Qiu, Weijun Fan, Ting He, Lei Lin, Haoran Zhang, Owen M. Park, George Sajan Elengikal, Yuxin Kang, Ang Chen, Mosharaf Chowdhury, Myungjin Lee, and Xinyu Wang. Iac-eval: A code generation benchmark for cloud infrastructureas- code programs. In The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2024."},{"key":"e_1_2_1_21_1","volume-title":"Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela. Retrievalaugmented generation for knowledge-intensive nlp tasks","author":"Lewis Patrick","year":"2021","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen tau Yih, Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela. Retrievalaugmented generation for knowledge-intensive nlp tasks, 2021."},{"key":"e_1_2_1_22_1","volume-title":"Alexandra Sasha Luccioni, and Giada Pistilli. Fully autonomous AI agents should not be developed","author":"Mitchell Margaret","year":"2025","unstructured":"Margaret Mitchell, Avijit Ghosh, Alexandra Sasha Luccioni, and Giada Pistilli. Fully autonomous AI agents should not be developed, 2025."},{"key":"e_1_2_1_23_1","volume-title":"Webgpt: Browser-assisted question-answering with human feedback","author":"Nakano Reiichiro","year":"2022","unstructured":"Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, Xu Jiang, Karl Cobbe, Tyna Eloundou, Gretchen Krueger, Kevin Button, Matthew Knight, Benjamin Chess, and John Schulman. Webgpt: Browser-assisted question-answering with human feedback, 2022."},{"key":"e_1_2_1_24_1","volume-title":"Gpt-4 technical report","author":"AI.","year":"2024","unstructured":"OpenAI. Gpt-4 technical report, 2024."},{"key":"e_1_2_1_25_1","volume-title":"Memgpt: Towards llms as operating systems","author":"Packer Charles","year":"2024","unstructured":"Charles Packer, Sarah Wooders, Kevin Lin, Vivian Fang, Shishir G. Patil, Ion Stoica, and Joseph E. Gonzalez. Memgpt: Towards llms as operating systems, 2024."},{"key":"e_1_2_1_26_1","volume-title":"Percy Liang, and Michael S.","author":"Park Joon Sung","year":"2023","unstructured":"Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, and Michael S. Bernstein. Generative agents: Interactive simulacra of human behavior, 2023."},{"key":"e_1_2_1_27_1","volume-title":"Raluca Ada Popa, and Ion Stoica. Goex: Perspectives and designs towards a runtime for autonomous llm applications","author":"Patil Shishir G.","year":"2024","unstructured":"Shishir G. Patil, Tianjun Zhang, Vivian Fang, Noppapon C., Roy Huang, Aaron Hao, Martin Casado, Joseph E. Gonzalez, Raluca Ada Popa, and Ion Stoica. Goex: Perspectives and designs towards a runtime for autonomous llm applications, 2024."},{"key":"e_1_2_1_28_1","volume-title":"Gorilla: Large language model connected with massive apis","author":"Patil Shishir G.","year":"2023","unstructured":"Shishir G. Patil, Tianjun Zhang, Xin Wang, and Joseph E. Gonzalez. Gorilla: Large language model connected with massive apis, 2023."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695974"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626111.3628206"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3698038.3698525"},{"key":"e_1_2_1_32_1","volume-title":"Reflexion: Language agents with verbal reinforcement learning","author":"Shinn Noah","year":"2023","unstructured":"Noah Shinn, Federico Cassano, Edward Berman, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. Reflexion: Language agents with verbal reinforcement learning, 2023."},{"key":"e_1_2_1_33_1","volume-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang Guanzhi","year":"2023","unstructured":"Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. Voyager: An open-ended embodied agent with large language models, 2023."},{"key":"e_1_2_1_34_1","volume-title":"Badagent: Inserting and activating backdoor attacks in llm agents","author":"Xue Dizhan","year":"2024","unstructured":"YifeiWang, Dizhan Xue, Shengjie Zhang, and Shengsheng Qian. Badagent: Inserting and activating backdoor attacks in llm agents, 2024."},{"key":"e_1_2_1_35_1","volume-title":"Agent workflow memory","author":"Wang Zora Zhiruo","year":"2024","unstructured":"Zora Zhiruo Wang, Jiayuan Mao, Daniel Fried, and Graham Neubig. Agent workflow memory, 2024."},{"key":"e_1_2_1_36_1","volume-title":"Chi, Quoc Le, and Denny Zhou. Chain-of-thought prompting elicits reasoning in large language models","author":"Wei Jason","year":"2023","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc Le, and Denny Zhou. Chain-of-thought prompting elicits reasoning in large language models, 2023."},{"key":"e_1_2_1_37_1","volume-title":"Multi-programming language ensemble for code generation in large language model","author":"Xue Tengfei","year":"2024","unstructured":"Tengfei Xue, Xuefeng Li, Tahir Azim, Roman Smirnov, Jianhui Yu, Arash Sadrieh, and Babak Pahlavan. Multi-programming language ensemble for code generation in large language model, 2024."},{"key":"e_1_2_1_38_1","volume-title":"Swe-agent: Agent-computer interfaces enable automated software engineering","author":"Yang John","year":"2024","unstructured":"John Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press. Swe-agent: Agent-computer interfaces enable automated software engineering, 2024."},{"key":"e_1_2_1_39_1","volume-title":"Watch out for your agents! investigating backdoor threats to llm-based agents","author":"Yang Wenkai","year":"2024","unstructured":"Wenkai Yang, Xiaohan Bi, Yankai Lin, Sishuo Chen, Jie Zhou, and Xu Sun. Watch out for your agents! investigating backdoor threats to llm-based agents, 2024."},{"key":"e_1_2_1_40_1","volume-title":"Webshop: Towards scalable real-world web interaction with grounded language agents","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Howard Chen, John Yang, and Karthik Narasimhan. Webshop: Towards scalable real-world web interaction with grounded language agents, 2023."},{"key":"e_1_2_1_41_1","volume-title":"Tree of thoughts: Deliberate problem solving with large language models","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L. Griffiths, Yuan Cao, and Karthik Narasimhan. Tree of thoughts: Deliberate problem solving with large language models, 2023."},{"key":"e_1_2_1_42_1","volume-title":"React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629","author":"Yao Shunyu","year":"2022","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629, 2022."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650212.3680384"},{"key":"e_1_2_1_44_1","volume-title":"Can models learn skill composition from examples?","author":"Zhao Haoyu","year":"2024","unstructured":"Haoyu Zhao, Simran Kaur, Dingli Yu, Anirudh Goyal, and Sanjeev Arora. Can models learn skill composition from examples?, 2024."},{"key":"e_1_2_1_45_1","volume-title":"Webarena: A realistic web environment for building autonomous agents","author":"Zhou Shuyan","year":"2024","unstructured":"Shuyan Zhou, Frank F. Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, Uri Alon, and Graham Neubig. Webarena: A realistic web environment for building autonomous agents, 2024."}],"container-title":["ACM SIGOPS Operating Systems Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3759441.3759443","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T19:50:38Z","timestamp":1754596238000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3759441.3759443"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,4]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,8,4]]}},"alternative-id":["10.1145\/3759441.3759443"],"URL":"https:\/\/doi.org\/10.1145\/3759441.3759443","relation":{},"ISSN":["0163-5980"],"issn-type":[{"value":"0163-5980","type":"print"}],"subject":[],"published":{"date-parts":[[2025,8,4]]},"assertion":[{"value":"2025-08-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}