{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T16:50:42Z","timestamp":1786812642941,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":110,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:00:00Z","timestamp":1732060800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,20]]},"DOI":"10.1145\/3698038.3698525","type":"proceedings-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T06:32:43Z","timestamp":1731565963000},"page":"99-110","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":30,"title":["Building AI Agents for Autonomous Clouds: Challenges and Design Principles"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8630-3998","authenticated-orcid":false,"given":"Manish","family":"Shetty","sequence":"first","affiliation":[{"name":"University of California, Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5408-2347","authenticated-orcid":false,"given":"Yinfang","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6949-8685","authenticated-orcid":false,"given":"Gagan","family":"Somashekar","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6303-1731","authenticated-orcid":false,"given":"Minghua","family":"Ma","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4140-7774","authenticated-orcid":false,"given":"Yogesh","family":"Simmhan","sequence":"additional","affiliation":[{"name":"Indian Institue of Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1492-0476","authenticated-orcid":false,"given":"Xuchao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3701-9296","authenticated-orcid":false,"given":"Jonathan","family":"Mace","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8627-5413","authenticated-orcid":false,"given":"Dax","family":"Vandevoorde","sequence":"additional","affiliation":[{"name":"Agnes Scott College"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7590-3736","authenticated-orcid":false,"given":"Pedro","family":"Las-Casas","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1332-690X","authenticated-orcid":false,"given":"Shachee Mishra","family":"Gupta","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7813-9756","authenticated-orcid":false,"given":"Suman","family":"Nath","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0102-8139","authenticated-orcid":false,"given":"Chetan","family":"Bansal","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0204-7187","authenticated-orcid":false,"given":"Saravan","family":"Rajmohan","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,20]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2022. AWS Fault Injection Simulator. https:\/\/aws.amazon.com\/fis\/."},{"key":"e_1_3_2_1_2_1","unstructured":"2022. Jepsen. https:\/\/jepsen.io\/."},{"key":"e_1_3_2_1_3_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_4_1","unstructured":"AgentOps-AI. 2024. agentops. https:\/\/github.com\/AgentOps-AI\/agentops."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00149"},{"key":"e_1_3_2_1_6_1","unstructured":"Aider. 2024. How aider scored SOTA 26.3% on SWE Bench Lite. https:\/\/aider.chat\/2024\/05\/22\/swe-bench-lite.html."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation (OSDI'16)","author":"Alagappan Ramnatthan","unstructured":"Ramnatthan Alagappan, Aishwarya Ganesan, Yuvraj Patel, Thanumalayan Sankaranarayana Pillai, Andrea C. Arpaci-Dusseau, and Remzi H. Arpaci-Dusseau. 2016. Correlated Crash Vulnerabilities. In Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation (OSDI'16)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/3291168.3291173"},{"key":"e_1_3_2_1_9_1","volume-title":"2018 USENIX Annual Technical Conference (USENIX ATC 18)","author":"Amvrosiadis George","year":"2018","unstructured":"George Amvrosiadis, Jun Woo Park, Gregory R. Ganger, Garth A. Gibson, Elisabeth Baseman, and Nathan DeBardeleben. 2018. On the diversity of cluster workloads and its impact on research results. In 2018 USENIX Annual Technical Conference (USENIX ATC 18). USENIX Association, Boston, MA, 533--546. https:\/\/www.usenix.org\/conference\/atc18\/presentation\/amvrosiadis"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613138"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3446346"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2168836.2168865"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377813.3381353"},{"key":"e_1_3_2_1_14_1","volume-title":"C\u00e9sar AF De Rose, and Rajkumar Buyya","author":"Calheiros Rodrigo N","year":"2011","unstructured":"Rodrigo N Calheiros, Rajiv Ranjan, Anton Beloglazov, C\u00e9sar AF De Rose, and Rajkumar Buyya. 2011. CloudSim: a toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms. Software: Practice and experience 41, 1 (2011), 23--50."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/2228298.2228312"},{"key":"e_1_3_2_1_16_1","unstructured":"Chaos Mesh Community. [n. d.]. ChaosMesh. https:\/\/chaos-mesh.org\/. Accessed: 2024-07-08."},{"key":"e_1_3_2_1_17_1","unstructured":"ChaosBlade Team. [n. d.]. ChaosBlade. https:\/\/github.com\/chaosblade-io\/chaosblade. Accessed: 2024-07-08."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3416548"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP.2019.00020"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00042"},{"key":"e_1_3_2_1_21_1","volume-title":"Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al.","author":"Chen Mark","year":"2021","unstructured":"Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde De Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629553"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2017.60"},{"key":"e_1_3_2_1_24_1","volume-title":"Self-healing and Hybrid Diagnosis in Cloud Computing","author":"Dai Yuanshun","unstructured":"Yuanshun Dai, Yanping Xiang, and Gewei Zhang. 2009. Self-healing and Hybrid Diagnosis in Cloud Computing. In Cloud Computing, Martin Gilje Jaatun, Gansen Zhao, and Chunming Rong (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3236447"},{"key":"e_1_3_2_1_26_1","unstructured":"Envoy Docs. 2022. Envoy Fault Injection. https:\/\/www.envoyproxy.io\/docs\/envoy\/latest\/api-v3\/extensions\/filters\/http\/fault\/v3\/fault.proto."},{"key":"e_1_3_2_1_27_1","volume-title":"Anastasia Ailamaki, and Babak Falsafi.","author":"Ferdman Michael","year":"2012","unstructured":"Michael Ferdman, Almutaz Adileh, Onur Kocberber, Stavros Volos, Mohammad Alisafaee, Djordje Jevdjic, Cansu Kaynak, Adrian Daniel Popescu, Anastasia Ailamaki, and Babak Falsafi. 2012. Clearing the clouds: a study of emerging scale-out workloads on modern hardware. Acm sigplan notices 47, 4 (2012), 37--48."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304013"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3613898"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCC.2018.053711662"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563482"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613161"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 8th USENIX Symposium on Networked Systems Design and Implementation (NSDI'11)","author":"Gunawi Haryadi S.","year":"2011","unstructured":"Haryadi S. Gunawi, Thanh Do, Pallavi Joshi, Peter Alvaro, Joseph M. Hellerstein, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau, Koushik Sen, and Dhruba Borthakur. 2011. Fate and Destini: A Framework for Cloud Recovery Testing. In Proceedings of the 8th USENIX Symposium on Networked Systems Design and Implementation (NSDI'11)."},{"key":"e_1_3_2_1_34_1","first-page":"32142","article-title":"Adbench: Anomaly detection benchmark","volume":"35","author":"Han Songqiao","year":"2022","unstructured":"Songqiao Han, Xiyang Hu, Hailiang Huang, Minqi Jiang, and Yue Zhao. 2022. Adbench: Anomaly detection benchmark. Advances in Neural Information Processing Systems 35 (2022), 32142--32159.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694347"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3613881"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3558963"},{"key":"e_1_3_2_1_38_1","volume-title":"Helm: The package manager for Kubernetes.","year":"2024","unstructured":"Helm. 2024. Helm: The package manager for Kubernetes."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2016.11"},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the 3rd USENIX Windows NT Symposium.","author":"Hunt Galen","year":"1999","unstructured":"Galen Hunt and Doug Brubacher. 1999. Detours: Binary Interception of Win32 Functions. In Proceedings of the 3rd USENIX Windows NT Symposium."},{"key":"e_1_3_2_1_41_1","unstructured":"Istio Docs. 2022. Istio Fault Injection. https:\/\/istio.io\/latest\/docs\/tasks\/traffic-management\/fault-injection\/."},{"key":"e_1_3_2_1_42_1","volume-title":"Anomalybench: An open benchmark for explainable anomaly detection. CoRR abs\/2010.05073","author":"Jacob Vincent","year":"2020","unstructured":"Vincent Jacob, Fei Song, Arnaud Stiegler, Yanlei Diao, and Nesime Tatbul. 2020. Anomalybench: An open benchmark for explainable anomaly detection. CoRR abs\/2010.05073 (2020)."},{"key":"e_1_3_2_1_43_1","volume-title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code. arXiv preprint arXiv:2403.07974","author":"Jain Naman","year":"2024","unstructured":"Naman Jain, King Han, Alex Gu, Wen-Ding Li, Fanjia Yan, Tianjun Zhang, Sida Wang, Armando Solar-Lezama, Koushik Sen, and Ion Stoica. 2024. LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code. arXiv preprint arXiv:2403.07974 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"Forty-first International Conference on Machine Learning.","author":"Jain Naman","year":"2024","unstructured":"Naman Jain, Manish Shetty, Tianjun Zhang, King Han, Koushik Sen, and Ion Stoica. 2024. R2E: Turning any Github Repository into a Programming Agent Environment. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417054"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.5555\/3489212.3489358"},{"key":"e_1_3_2_1_47_1","volume-title":"The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=VTF8yNQM66","author":"Jimenez Carlos E","year":"2024","unstructured":"Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R Narasimhan. 2024. SWE-bench: Can Language Models Resolve Real-world Github Issues?. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=VTF8yNQM66"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3613891"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2523616.2523622"},{"key":"e_1_3_2_1_50_1","volume-title":"AI Agents That Matter. arXiv preprint arXiv:2407.01502","author":"Kapoor Sayash","year":"2024","unstructured":"Sayash Kapoor, Benedikt Stroebl, Zachary S Siegel, Nitya Nadgir, and Arvind Narayanan. 2024. AI Agents That Matter. arXiv preprint arXiv:2407.01502 (2024)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2016.7581261"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Nane Kratzke and Peter-Christian Quint.2016. ppbench-A Visualizing Network Benchmark for Microservices.. In CLOSER (2). 223--231.","DOI":"10.5220\/0005732202230231"},{"key":"e_1_3_2_1_53_1","volume-title":"XFBench: A Cross-Cloud Benchmark Suite for Evaluating FaaS Workflow Platforms. In 24th IEEE\/ACM international Symposium on Cluster, Cloud and Internet Computing (CCGRID).","author":"Varad","unstructured":"Varad Kulkarni et al. 2024. XFBench: A Cross-Cloud Benchmark Suite for Evaluating FaaS Workflow Platforms. In 24th IEEE\/ACM international Symposium on Cluster, Cloud and Internet Computing (CCGRID)."},{"key":"e_1_3_2_1_54_1","volume-title":"Proceedings of the 11th USENIX Conference on Operating Systems Design and Implementation (OSDI'14)","author":"Leesatapornwongsa Tanakorn","unstructured":"Tanakorn Leesatapornwongsa, Mingzhe Hao, Pallavi Joshi, Jeffrey F. Lukman, and Haryadi S. Gunawi. 2014. SAMC: Semantic-Aware Model Checking for Fast Discovery of Deep Bugs in Cloud Systems. In Proceedings of the 11th USENIX Conference on Operating Systems Design and Implementation (OSDI'14)."},{"key":"e_1_3_2_1_55_1","volume-title":"2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Li Liqun","year":"2021","unstructured":"Liqun Li, Xu Zhang, Xin Zhao, Hongyu Zhang, Yu Kang, Pu Zhao, Bo Qiao, Shilin He, Pochian Lee, Jeffrey Sun, et al. 2021. Fighting the fog of war: Automated incident detection for cloud systems. In 2021 USENIX Annual Technical Conference (USENIX ATC 21). 131--146."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS.2012.109"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/IWQOS52092.2021.9521340"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"e_1_3_2_1_59_1","volume-title":"Agent-bench: Evaluating llms as agents. arXiv preprint arXiv:2308.03688","author":"Liu Xiao","year":"2023","unstructured":"Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu, Hangliang Ding, Kaiwen Men, Kejuan Yang, et al. 2023. Agent-bench: Evaluating llms as agents. arXiv preprint arXiv:2308.03688 (2023)."},{"key":"e_1_3_2_1_60_1","unstructured":"Yuhe Liu Changhua Pei Longlong Xu Bohan Chen Mingze Sun Zhirui Zhang Yongqian Sun Shenglin Zhang Kun Wang Haiming Zhang et al. 2023. OpsEval: A Comprehensive Task-Oriented AIOps Benchmark for Large Language Models. arXiv preprint arXiv:2310.07637 (2023)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359645"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.14778\/3389133.3389136"},{"key":"e_1_3_2_1_63_1","volume-title":"Jump-Starting Multivariate Time Series Anomaly Detection for Online Service Systems. In 2021 USENIX Annual Technical Conference (ATC'21)","author":"Ma Minghua","year":"2021","unstructured":"Minghua Ma, Shenglin Zhang, Junjie Chen, Jim Xu, Haozhe Li, Yongliang Lin, Xiaohui Nie, Bo Zhou, Yong Wang, and Dan Pei. 2021. Jump-Starting Multivariate Time Series Anomaly Detection for Online Service Systems. In 2021 USENIX Annual Technical Conference (ATC'21)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE.2018.00013"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3158134"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.5555\/1855840.1855863"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2009.5270313"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063509.2063511"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3487005"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.5555\/3291168.3291172"},{"key":"e_1_3_2_1_71_1","unstructured":"Netflix. [n.d.]. ChaosMonkey. https:\/\/github.com\/Netflix\/chaosmonkey. Accessed: 2024-07-08."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3483424"},{"key":"e_1_3_2_1_73_1","volume-title":"Proceedings of the 11th USENIX Conference on Operating Systems Design and Implementation (OSDI'14)","author":"Pillai Thanumalayan Sankaranarayana","unstructured":"Thanumalayan Sankaranarayana Pillai, Vijay Chidambaram, Samer Al Kiswany, Andrea C. Arpaci-Dusseau, and Remzi H. Arpaci-Dusseau. 2014. All File Systems Are Not Created Equal: On the Complexity of Crafting Crash-Consistent Applications. In Proceedings of the 11th USENIX Conference on Operating Systems Design and Implementation (OSDI'14)."},{"key":"e_1_3_2_1_74_1","unstructured":"Reuters. 2023. Microsoft cloud outage hits users around the world. (2023). https:\/\/www.cnn.com\/2023\/01\/25\/tech\/microsoft-cloud-outage-worldwide-trnd\/index.html"},{"key":"e_1_3_2_1_75_1","volume-title":"Proceedings of the 3rd USENIX Symposium on Networked Systems Design and Implementation (NSDI'06)","author":"Reynolds Patrick","year":"2006","unstructured":"Patrick Reynolds, Charles Killian, Janet L. Wiener, Jeffrey C. Mogul, Mehul A. Shah, and Amin Vahdat. 2006. Pip: Detecting the Unexpected in Distributed Systems. In Proceedings of the 3rd USENIX Symposium on Networked Systems Design and Implementation (NSDI'06)."},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3512759"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3558958"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2021.04.001"},{"key":"e_1_3_2_1_79_1","volume-title":"14th Conference on Innovative Data Systems Research, CIDR 2024","author":"Singh Vikramank Y.","year":"2024","unstructured":"Vikramank Y. Singh, Kapil Vaidya, Vinayshekhar Bannihatti Kumar, Sopan Khosla, Balakrishnan Narayanaswamy, Rashmi Gangadharaiah, and Tim Kraska. 2024. Panda: Performance Debugging for Databases using LLM Agents. In 14th Conference on Innovative Data Systems Research, CIDR 2024, Chaminade, HI, USA, January 14-17, 2024."},{"key":"e_1_3_2_1_80_1","volume-title":"From Clouds to Hybrid Clouds. ACM India Minigraphs","author":"Singhee Amith","year":"2023","unstructured":"Amith Singhee and Praveen Jayachandran. 2023. From Clouds to Hybrid Clouds. ACM India Minigraphs (2023)."},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645665"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491204.3527494"},{"key":"e_1_3_2_1_83_1","volume-title":"a benchmark suite for microservices. In 2018 ieee international symposium on workload characterization (iiswc)","author":"Sriraman Akshitha","unstructured":"Akshitha Sriraman and Thomas F Wenisch. 2018. μ suite: a benchmark suite for microservices. In 2018 ieee international symposium on workload characterization (iiswc). IEEE, 1--12."},{"key":"e_1_3_2_1_84_1","unstructured":"Laura Stevens. 2017. Amazon Finds the Cause of Its AWS Outage: A Typo. (2017). https:\/\/www.wsj.com\/articles\/amazon-finds-the-cause-of-its-aws-outage-a-typo-1488490506"},{"key":"e_1_3_2_1_85_1","volume-title":"Proceedings of the 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI'22)","author":"Sun Xudong","year":"2022","unstructured":"Xudong Sun, Wenqing Luo, Jiawei Tyler Gu, Aishwarya Ganesan, Ramnatthan Alagappan, Michael Gasch, Lalith Suresh, and Tianyin Xu. 2022. Automatic Reliability Testing for Cluster Management Controllers. In Proceedings of the 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI'22)."},{"key":"e_1_3_2_1_86_1","volume-title":"Overleaf: An open-source online real-time collaborative LaTeX editor","author":"Team The Overleaf","year":"2024","unstructured":"The Overleaf Team. 2024. Overleaf: An open-source online real-time collaborative LaTeX editor. https:\/\/github.com\/overleaf\/overleaf."},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2016.7581269"},{"key":"e_1_3_2_1_88_1","unstructured":"Laurens Versluis Roland Math\u00e1 Sacheendra Talluri Tim Hegeman Radu Prodan Ewa Deelman and Alexandru Iosup. 2019. The Workflow Trace Archive: Open-Access Data from Public and Private Computing Infrastructures - Technical Report. CoRR abs\/1906.07471 (2019). arXiv:1906.07471 http:\/\/arxiv.org\/abs\/1906.07471"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOTS.2018.00030"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835958"},{"key":"e_1_3_2_1_91_1","volume-title":"Rcagent: Cloud root cause analysis by autonomous agents with tool-augmented large language models. arXiv preprint arXiv:2310.16340","author":"Wang Zefan","year":"2023","unstructured":"Zefan Wang, Zichuan Liu, Yingying Zhang, Aoxiao Zhong, Lunting Fan, Lingfei Wu, and Qingsong Wen. 2023. Rcagent: Cloud root cause analysis by autonomous agents with tool-augmented large language models. arXiv preprint arXiv:2310.16340 (2023)."},{"key":"e_1_3_2_1_92_1","unstructured":"Sean Wolfe. 2018. Amazon's one hour of downtime on Prime Day may have cost it up to $100 million in lost sales. (2018). https:\/\/www.businessinsider.com\/amazon-prime-day-website-issues-cost-it-millions-in-lost-sales-2018-7"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583215"},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP58684.2023.00026"},{"key":"e_1_3_2_1_95_1","volume-title":"Swe-agent: Agent-computer interfaces enable automated software engineering. arXiv preprint arXiv:2405.15793","author":"Yang John","year":"2024","unstructured":"John Yang, Carlos E Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press. 2024. Swe-agent: Agent-computer interfaces enable automated software engineering. arXiv preprint arXiv:2405.15793 (2024)."},{"key":"e_1_3_2_1_96_1","volume-title":"ReAct: Synergizing Reasoning and Acting in Language Models. In International Conference on Learning Representations (ICLR).","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. ReAct: Synergizing Reasoning and Acting in Language Models. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421280"},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2021.24549"},{"key":"e_1_3_2_1_99_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833669"},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"crossref","unstructured":"Zhengran Zeng Yuqun Zhang Yong Xu Minghua Ma Bo Qiao Wentao Zou Qingjun Chen Meng Zhang Xu Zhang Hongyu Zhang Xuedong Gao Hao Fan Saravan Rajmohan Qingwei Lin and Dongmei Zhang. 2023. TraceArk: Towards Actionable Performance Anomaly Alerting for Online Service Systems. In To appear in Proc. of ICSE.","DOI":"10.1109\/ICSE-SEIP58684.2023.00029"},{"key":"e_1_3_2_1_101_1","doi-asserted-by":"publisher","DOI":"10.5555\/2337223.2337293"},{"key":"e_1_3_2_1_102_1","volume-title":"Proceedings of the 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI'18)","author":"Zhang Qiao","year":"2018","unstructured":"Qiao Zhang, Guo Yu, Chuanxiong Guo, Yingnong Dang, Nick Swanson, Xinsheng Yang, Randolph Yao, Murali Chintalapati, Arvind Krishnamurthy, and Thomas Anderson. 2018. Deepview: Virtual Disk Failure Diagnosis and Pattern Detection for Azure. In Proceedings of the 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI'18)."},{"key":"e_1_3_2_1_103_1","doi-asserted-by":"publisher","DOI":"10.1145\/3663529.3663846"},{"key":"e_1_3_2_1_104_1","volume-title":"Autocoderover: Autonomous program improvement. arXiv preprint arXiv:2404.05427","author":"Zhang Yuntong","year":"2024","unstructured":"Yuntong Zhang, Haifeng Ruan, Zhiyu Fan, and Abhik Roychoudhury. 2024. Autocoderover: Autonomous program improvement. arXiv preprint arXiv:2404.05427 (2024)."},{"key":"e_1_3_2_1_105_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599902"},{"key":"e_1_3_2_1_106_1","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric Xing et al. 2024. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_107_1","unstructured":"Shuyan Zhou Frank F Xu Hao Zhu Xuhui Zhou Robert Lo Abishek Sridhar Xianyi Cheng Yonatan Bisk Daniel Fried Uri Alon et al. 2023. WebArena: A Realistic Web Environment for Building Autonomous Agents. arXiv preprint arXiv:2307.13854 (2023). https:\/\/webarena.dev"},{"key":"e_1_3_2_1_108_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183440.3194991"},{"key":"e_1_3_2_1_109_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183440.3194991"},{"key":"e_1_3_2_1_110_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP.2019.00021"}],"event":{"name":"SoCC '24: ACM Symposium on Cloud Computing","location":"Redmond WA USA","acronym":"SoCC '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the ACM Symposium on Cloud Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3698038.3698525","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3698038.3698525","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T19:00:06Z","timestamp":1755889206000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3698038.3698525"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,20]]},"references-count":110,"alternative-id":["10.1145\/3698038.3698525","10.1145\/3698038"],"URL":"https:\/\/doi.org\/10.1145\/3698038.3698525","relation":{},"subject":[],"published":{"date-parts":[[2024,11,20]]},"assertion":[{"value":"2024-11-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}