{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:07:01Z","timestamp":1784300821694,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,5]]},"DOI":"10.1145\/3803437.3805241","type":"proceedings-article","created":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:27:39Z","timestamp":1784298459000},"page":"690-701","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Aloha: Localizing Batch Failures in Large-scale Cloud Systems via Contrast Analysis and Human-in-the-Loop Agent"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0330-0028","authenticated-orcid":false,"given":"Shenglin","family":"Zhang","sequence":"first","affiliation":[{"name":"Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9443-9846","authenticated-orcid":false,"given":"Yujia","family":"Wu","sequence":"additional","affiliation":[{"name":"Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9686-0464","authenticated-orcid":false,"given":"Jinghuan","family":"Ren","sequence":"additional","affiliation":[{"name":"Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0266-7899","authenticated-orcid":false,"given":"Yongqian","family":"Sun","sequence":"additional","affiliation":[{"name":"Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1096-2732","authenticated-orcid":false,"given":"Wenwei","family":"Gu","sequence":"additional","affiliation":[{"name":"Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1304-6839","authenticated-orcid":false,"given":"Chaoyun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4579-3799","authenticated-orcid":false,"given":"Liqun","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2559-2383","authenticated-orcid":false,"given":"Qingwei","family":"Lin","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9230-2799","authenticated-orcid":false,"given":"Dongmei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"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, Redmond, USA"}],"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, Redmond, USA"}],"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, Redmond, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Nissist: An incident mitigation copilot based on troubleshooting guides. arXiv preprint arXiv:2402.17531","author":"An Kaikai","year":"2024","unstructured":"Kaikai An, Fangkai Yang, Junting Lu, Liqun Li, Zhixing Ren, Hao Huang, Lu Wang, Pu Zhao, Yu Kang, Hua Ding, et al. 2024. Nissist: An incident mitigation copilot based on troubleshooting guides. arXiv preprint arXiv:2402.17531 (2024)."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining. 302\u2013306","author":"Bay Stephen D","year":"1999","unstructured":"Stephen D Bay and Michael J Pazzani. 1999. Detecting change in categorical data: Mining contrast sets. In Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining. 302\u2013306."},{"key":"e_1_3_2_1_3_1","volume-title":"Jake Pencharz, Oliver Sourbut, Michael Schmatz, Jay Bailey, Ollie Matthews, Ben Millwood, Alex Remedios, and Alan Cooney.","author":"Black Sid","year":"2025","unstructured":"Sid Black, Asa Cooper Stickland, Jake Pencharz, Oliver Sourbut, Michael Schmatz, Jay Bailey, Ollie Matthews, Ben Millwood, Alex Remedios, and Alan Cooney. 2025. RepliBench: Evaluating the Autonomous Replication Capabilities of Language Model Agents. arXiv preprint arXiv:2504.18565 (2025)."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 2017 11th Joint Meeting on Foundations of Software Engineering. 717\u2013726","author":"Castelluccio Marco","year":"2017","unstructured":"Marco Castelluccio, Carlo Sansone, Luisa Verdoliva, and Giovanni Poggi. 2017. Automatically analyzing groups of crashes for finding correlations. In Proceedings of the 2017 11th Joint Meeting on Foundations of Software Engineering. 717\u2013726."},{"key":"e_1_3_2_1_5_1","volume-title":"2019 IEEE\/ACM 41st International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). IEEE, 111\u2013120","author":"Chen Junjie","year":"2019","unstructured":"Junjie Chen, Xiaoting He, Qingwei Lin, Yong Xu, Hongyu Zhang, Dan Hao, Feng Gao, Zhangwei Xu, Yingnong Dang, and Dongmei Zhang. 2019. An empirical investigation of incident triage for online service systems. In 2019 IEEE\/ACM 41st International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). IEEE, 111\u2013120."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the Nineteenth European Conference on Computer Systems. 674\u2013688","author":"Chen Yinfang","year":"2024","unstructured":"Yinfang Chen, Huaibing Xie, Minghua Ma, Yu Kang, Xin Gao, Liu Shi, Yunjie Cao, Xuedong Gao, Hao Fan, Ming Wen, et al. 2024. Automatic root cause analysis via large language models for cloud incidents. In Proceedings of the Nineteenth European Conference on Computer Systems. 674\u2013688."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Dong Guozhu","year":"1999","unstructured":"Guozhu Dong and Jinyan Li. 1999. Efficient mining of emerging patterns: discovering trends and differences. In Proceedings of the Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (San Diego, California, USA) (KDD '99). Association for Computing Machinery, New York, NY, USA, 43\u201352. 10.1145\/312129.312191"},{"key":"e_1_3_2_1_8_1","volume-title":"DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents. arXiv preprint arXiv:2506.11763","author":"Du Mingxuan","year":"2025","unstructured":"Mingxuan Du, Benfeng Xu, Chiwei Zhu, Xiaorui Wang, and Zhendong Mao. 2025. DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents. arXiv preprint arXiv:2506.11763 (2025)."},{"key":"e_1_3_2_1_9_1","volume-title":"System Safety Conference","volume":"1","author":"Ericson Clifton A","year":"1999","unstructured":"Clifton A Ericson and Clifton Ll. 1999. Fault tree analysis. In System Safety Conference, Orlando, Florida, Vol. 1. 1\u20139."},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining. 6491\u20136501","author":"Fan Wenqi","year":"2024","unstructured":"Wenqi Fan, Yujuan Ding, Liangbo Ning, Shijie Wang, Hengyun Li, Dawei Yin, Tat-Seng Chua, and Qing Li. 2024. A survey on rag meeting llms: Towards retrieval-augmented large language models. In Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining. 6491\u20136501."},{"key":"e_1_3_2_1_11_1","first-page":"1","article-title":"Contrast analysis: A tutorial","volume":"23","author":"Haans Antal","year":"2018","unstructured":"Antal Haans. 2018. Contrast analysis: A tutorial. Practical Assessment, Research & Evaluation 23, 9 (2018), 1\u201321.","journal-title":"Practical Assessment, Research & Evaluation"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 2018 26th ACM joint meeting on European software engineering conference and symposium on the foundations of software engineering. 60\u201370","author":"He Shilin","year":"2018","unstructured":"Shilin He, Qingwei Lin, Jian-Guang Lou, Hongyu Zhang, Michael R Lyu, and Dongmei Zhang. 2018. Identifying impactful service system problems via log analysis. In Proceedings of the 2018 26th ACM joint meeting on European software engineering conference and symposium on the foundations of software engineering. 60\u201370."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 1465\u20131476","author":"He Shilin","year":"2022","unstructured":"Shilin He, Xu Zhang, Pinjia He, Yong Xu, Liqun Li, Yu Kang, Minghua Ma, Yining Wei, Yingnong Dang, Saravanakumar Rajmohan, et al. 2022. An empirical study of log analysis at Microsoft. In Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 1465\u20131476."},{"key":"e_1_3_2_1_14_1","unstructured":"Sirui Hong Yizhang Lin Bang Liu Bangbang Liu Binhao Wu Ceyao Zhang Chenxing Wei Danyang Li Jiaqi Chen Jiayi Zhang et al. 2024. Data interpreter: An llm agent for data science. arXiv preprint arXiv:2402.18679 (2024)."},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering. 1\u201313","author":"Jiang Yuxuan","year":"2024","unstructured":"Yuxuan Jiang, Chaoyun Zhang, Shilin He, Zhihao Yang, Minghua Ma, Si Qin, Yu Kang, Yingnong Dang, Saravan Rajmohan, Qingwei Lin, et al. 2024. Xpert: Empowering incident management with query recommendations via large language models. In Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering. 1\u201313."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 1657\u20131668","author":"Jin Pengxiang","year":"2023","unstructured":"Pengxiang Jin, Shenglin Zhang, Minghua Ma, Haozhe Li, Yu Kang, Liqun Li, Yudong Liu, Bo Qiao, Chaoyun Zhang, Pu Zhao, et al. 2023. Assess and summarize: Improve outage understanding with large language models. In Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 1657\u20131668."},{"key":"e_1_3_2_1_17_1","volume-title":"ChiMerge: Discretization of Numeric Attributes","author":"Kerber Randy","year":"1992","unstructured":"Randy Kerber. 1992. ChiMerge: Discretization of Numeric Attributes. AAAI Press (1992)."},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 46th International Conference on Software Engineering: Software Engineering in Practice. 369\u2013380","author":"Kuang Jinxi","year":"2024","unstructured":"Jinxi Kuang, Jinyang Liu, Junjie Huang, Renyi Zhong, Jiazhen Gu, Lan Yu, Rui Tan, Zengyin Yang, and Michael R Lyu. 2024. Knowledge-aware alert aggregation in large-scale cloud systems: a hybrid approach. In Proceedings of the 46th International Conference on Software Engineering: Software Engineering in Practice. 369\u2013380."},{"key":"e_1_3_2_1_19_1","unstructured":"Patrick Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems 33 (2020) 9459\u20139474."},{"key":"e_1_3_2_1_20_1","volume-title":"2023 IEEE\/ACM 45th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). IEEE, 138\u2013149","author":"Li Liqun","year":"2023","unstructured":"Liqun Li, Xu Zhang, Shilin He, Yu Kang, Hongyu Zhang, Minghua Ma, Yingnong Dang, Zhangwei Xu, Saravan Rajmohan, Qingwei Lin, et al. 2023. Conan: Diagnosing batch failures for cloud systems. In 2023 IEEE\/ACM 45th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). IEEE, 138\u2013149."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","first-page":"111748","DOI":"10.1016\/j.jss.2023.111748","article-title":"Generic and robust root cause localization for multi-dimensional data in online service systems","volume":"203","author":"Li Zeyan","year":"2023","unstructured":"Zeyan Li, Junjie Chen, Yihao Chen, Chengyang Luo, Yiwei Zhao, Yongqian Sun, Kaixin Sui, Xiping Wang, Dapeng Liu, Xing Jin, et al. 2023. Generic and robust root cause localization for multi-dimensional data in online service systems. Journal of Systems and Software 203 (2023), 111748.","journal-title":"Journal of Systems and Software"},{"key":"e_1_3_2_1_22_1","volume-title":"2019 IEEE 30th International Symposium on Software Reliability Engineering (ISSRE). IEEE, 47\u201357","author":"Li Zeyan","year":"2019","unstructured":"Zeyan Li, Chengyang Luo, Yiwei Zhao, Yongqian Sun, Kaixin Sui, Xiping Wang, Dapeng Liu, Xing Jin, Qi Wang, and Dan Pei. 2019. Generic and robust localization of multi-dimensional root causes. In 2019 IEEE 30th International Symposium on Software Reliability Engineering (ISSRE). IEEE, 47\u201357."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 38th International Conference on Software Engineering. 214\u2013224","author":"Lin Qingwei","year":"2016","unstructured":"Qingwei Lin, Jian-Guang Lou, Hongyu Zhang, and Dongmei Zhang. 2016. iDice: Problem identification for emerging issues. In Proceedings of the 38th International Conference on Software Engineering. 214\u2013224."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2. 4623\u20134634","author":"Liu Jun","year":"2025","unstructured":"Jun Liu, Chaoyun Zhang, Jiaxu Qian, Minghua Ma, Si Qin, Chetan Bansal, Qingwei Lin, Saravan Rajmohan, and Dongmei Zhang. 2025. Large language models can deliver accurate and interpretable time series anomaly detection. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2. 4623\u20134634."},{"key":"e_1_3_2_1_25_1","volume-title":"Opseval: A comprehensive benchmark suite for evaluating large language models' capability in it operations domain. arXiv preprint arXiv:2310.07637","author":"Liu Yuhe","year":"2023","unstructured":"Yuhe Liu, Changhua Pei, Longlong Xu, Bohan Chen, Mingze Sun, Zhirui Zhang, Yongqian Sun, Shenglin Zhang, Kun Wang, Haiming Zhang, Minghua Ma, and Dan Pei. 2023. Opseval: A comprehensive benchmark suite for evaluating large language models' capability in it operations domain. arXiv preprint arXiv:2310.07637 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"Preliminary Post Incident Review - Multi-service impact in Switzerland North. https:\/\/azure.status.microsoft\/en-us\/status\/history\/. Accessed","author":"Azure Microsoft","year":"2025","unstructured":"Microsoft Azure. 2025. Preliminary Post Incident Review - Multi-service impact in Switzerland North. https:\/\/azure.status.microsoft\/en-us\/status\/history\/. Accessed: October 5, 2025."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","first-page":"3005","DOI":"10.1007\/s10462-022-10246-w","article-title":"Human-in-the-loop machine learning: a state of the art","volume":"56","author":"Mosqueira-Rey Eduardo","year":"2023","unstructured":"Eduardo Mosqueira-Rey, Elena Hern\u00e1ndez-Pereira, David Alonso-R\u00edos, Jos\u00e9 Bobes-Bascar\u00e1n, and \u00c1ngel Fern\u00e1ndez-Leal. 2023. Human-in-the-loop machine learning: a state of the art. Artificial Intelligence Review 56, 4 (2023), 3005\u20133054.","journal-title":"Artificial Intelligence Review"},{"key":"e_1_3_2_1_28_1","volume-title":"2021 IEEE\/ACM 43rd International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). IEEE, 288\u2013297","author":"Murali Vijayaraghavan","year":"2021","unstructured":"Vijayaraghavan Murali, Edward Yao, Umang Mathur, and Satish Chandra. 2021. Scalable statistical root cause analysis on app telemetry. In 2021 IEEE\/ACM 43rd International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). IEEE, 288\u2013297."},{"key":"e_1_3_2_1_29_1","volume-title":"9th USENIX Symposium on Networked Systems Design and Implementation (NSDI 12)","author":"Nagaraj Karthik","year":"2012","unstructured":"Karthik Nagaraj, Charles Killian, and Jennifer Neville. 2012. Structured comparative analysis of systems logs to diagnose performance problems. In 9th USENIX Symposium on Networked Systems Design and Implementation (NSDI 12). 353\u2013366."},{"key":"e_1_3_2_1_30_1","volume-title":"Flow-of-Action: SOP Enhanced LLM-Based Multi-Agent System for Root Cause Analysis. In Companion Proceedings of the ACM on Web Conference","author":"Pei Changhua","year":"2025","unstructured":"Changhua Pei, Zexin Wang, Fengrui Liu, Zeyan Li, Yang Liu, Xiao He, Rong Kang, Tieying Zhang, Jianjun Chen, Jianhui Li, et al. 2025. Flow-of-Action: SOP Enhanced LLM-Based Multi-Agent System for Root Cause Analysis. In Companion Proceedings of the ACM on Web Conference 2025. 422\u2013431."},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the ACM\/IEEE 42nd International Conference on Software Engineering: Software Engineering in Practice. 61\u201370","author":"Qian Rebecca","year":"2020","unstructured":"Rebecca Qian, Yang Yu, Wonhee Park, Vijayaraghavan Murali, Stephen Fink, and Satish Chandra. 2020. Debugging crashes using continuous contrast set mining. In Proceedings of the ACM\/IEEE 42nd International Conference on Software Engineering: Software Engineering in Practice. 61\u201370."},{"key":"e_1_3_2_1_32_1","volume-title":"Taskweaver: A code-first agent framework. arXiv preprint arXiv:2311.17541","author":"Qiao Bo","year":"2023","unstructured":"Bo Qiao, Liqun Li, Xu Zhang, Shilin He, Yu Kang, Chaoyun Zhang, Fangkai Yang, Hang Dong, Jue Zhang, Lu Wang, et al. 2023. Taskweaver: A code-first agent framework. arXiv preprint arXiv:2311.17541 (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Ren Xiang Jenny","year":"2023","unstructured":"Xiang Jenny Ren, Sitao Wang, Zhuqi Jin, David Lion, Adrian Chiu, Tianyin Xu, and Ding Yuan. 2023. Relational Debugging\u2014Pinpointing Root Causes of Performance Problems. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23). 65\u201380."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1613\/jair.1.15348","article-title":"Human-in-the-loop reinforcement learning: A survey and position on requirements, challenges, and opportunities","volume":"79","author":"Retzlaff Carl Orge","year":"2024","unstructured":"Carl Orge Retzlaff, Srijita Das, Christabel Wayllace, Payam Mousavi, Mohammad Afshari, Tianpei Yang, Anna Saranti, Alessa Angerschmid, Matthew E Taylor, and Andreas Holzinger. 2024. Human-in-the-loop reinforcement learning: A survey and position on requirements, challenges, and opportunities. Journal of Artificial Intelligence Research 79 (2024), 359\u2013415.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"e_1_3_2_1_35_1","volume-title":"8th USENIX Symposium on Networked Systems Design and Implementation (NSDI 11)","author":"Sambasivan Raja R","year":"2011","unstructured":"Raja R Sambasivan, Alice X Zheng, Michael De Rosa, Elie Krevat, Spencer Whitman, Michael Stroucken, William Wang, Lianghong Xu, and Gregory R Ganger. 2011. Diagnosing performance changes by comparing request flows. In 8th USENIX Symposium on Networked Systems Design and Implementation (NSDI 11)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","first-page":"38154","DOI":"10.52202\/075280-1657","article-title":"Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face","volume":"36","author":"Shen Yongliang","year":"2023","unstructured":"Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, and Yueting Zhuang. 2023. Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face. Advances in Neural Information Processing Systems 36 (2023), 38154\u201338180.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the 2024 ACM Symposium on Cloud Computing. 99\u2013110","author":"Shetty Manish","year":"2024","unstructured":"Manish Shetty, Yinfang Chen, Gagan Somashekar, Minghua Ma, Yogesh Simmhan, Xuchao Zhang, Jonathan Mace, Dax Vandevoorde, Pedro Las-Casas, Shachee Mishra Gupta, et al. 2024. Building AI Agents for Autonomous Clouds: Challenges and Design Principles. In Proceedings of the 2024 ACM Symposium on Cloud Computing. 99\u2013110."},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2. 4839\u20134850","author":"Shi Binpeng","year":"2025","unstructured":"Binpeng Shi, Yu Luo, Jingya Wang, Yongxin Zhao, Shenglin Zhang, Bowen Hao, Chenyu Zhao, Yongqian Sun, Zhi Zhang, Ronghua Sun, et al. 2025. FlowXpert: Expertizing Troubleshooting Workflow Orchestration with Knowledge Base and Multi-Agent Coevolution. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2. 4839\u20134850."},{"key":"e_1_3_2_1_39_1","volume-title":"The 10 Biggest Cloud Outages of 2025 (So Far). CRN","author":"Staff CRN","year":"2025","unstructured":"CRN Staff. 2025. The 10 Biggest Cloud Outages of 2025 (So Far). CRN (2025). https:\/\/www.crn.com\/news\/cloud\/2025\/the-10-biggest-cloud-outages-of-2025-so-far Accessed: 2025-10-05."},{"key":"e_1_3_2_1_40_1","first-page":"1387","article-title":"Robust anomaly clue localization of multi-dimensional derived measure for online video services","volume":"16","author":"Sun Yongqian","year":"2022","unstructured":"Yongqian Sun, Daguo Cheng, Pengxiang Jin, Quan Ding, Shenglin Zhang, Xu Chen, Yuzhi Zhang, Minghan Liang, Dan Pei, Jianyan Zheng, et al. 2022. Robust anomaly clue localization of multi-dimensional derived measure for online video services. IEEE Transactions on Services Computing 16, 2 (2022), 1387\u20131401.","journal-title":"IEEE Transactions on Services Computing"},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering. 1183\u20131194","author":"Sun Yongqian","year":"2024","unstructured":"Yongqian Sun, Binpeng Shi, Mingyu Mao, Minghua Ma, Sibo Xia, Shenglin Zhang, and Dan Pei. 2024. ART: A Unified Unsupervised Framework for Incident Management in Microservice Systems. In Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering. 1183\u20131194."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","first-page":"10909","DOI":"10.1109\/ACCESS.2018.2804764","article-title":"Hotspot: Anomaly localization for additive kpis with multi-dimensional attributes","volume":"6","author":"Sun Yongqian","year":"2018","unstructured":"Yongqian Sun, Youjian Zhao, Ya Su, Dapeng Liu, Xiaohui Nie, Yuan Meng, Shiwen Cheng, Dan Pei, Shenglin Zhang, Xianping Qu, et al. 2018. Hotspot: Anomaly localization for additive kpis with multi-dimensional attributes. IEEE Access 6 (2018), 10909\u201310923.","journal-title":"IEEE Access"},{"key":"e_1_3_2_1_43_1","volume-title":"2024 IEEE 35th International Symposium on Software Reliability Engineering (ISSRE). IEEE, 523\u2013534","author":"Wang Zexin","year":"2024","unstructured":"Zexin Wang, Jianhui Li, Minghua Ma, Ze Li, Yu Kang, Chaoyun Zhang, Chetan Bansal, Murali Chintalapati, Saravan Rajmohan, Qingwei Lin, et al. 2024. Large language models can provide accurate and interpretable incident triage. In 2024 IEEE 35th International Symposium on Software Reliability Engineering (ISSRE). IEEE, 523\u2013534."},{"key":"e_1_3_2_1_44_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems 35 (2022), 24824\u201324837."},{"key":"e_1_3_2_1_45_1","volume-title":"Proceedings of the 2014 International Symposium on Software Testing and Analysis. 204\u2013214","author":"Wu Rongxin","year":"2014","unstructured":"Rongxin Wu, Hongyu Zhang, Shing-Chi Cheung, and Sunghun Kim. 2014. Crashlocator: Locating crashing faults based on crash stacks. In Proceedings of the 2014 International Symposium on Software Testing and Analysis. 204\u2013214."},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings of the 19th international conference on architectural support for programming languages and operating systems. 193\u2013206","author":"Yu Xiao","year":"2014","unstructured":"Xiao Yu, Shi Han, Dongmei Zhang, and Tao Xie. 2014. Comprehending performance from real-world execution traces: A device-driver case. In Proceedings of the 19th international conference on architectural support for programming languages and operating systems. 193\u2013206."},{"key":"e_1_3_2_1_47_1","volume-title":"Triangle: Empowering Incident Triage with Multi-Agent. In 2025 40th IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE, 674\u2013686","author":"Yu Zhaoyang","year":"2025","unstructured":"Zhaoyang Yu, Aoyang Fang, Minghua Ma, Jaskaran Singh Walia, Chaoyun Zhang, Shu Chi, Ze Li, Murali Chintalapati, Xuchao Zhang, Rujia Wang, et al. 2025. Triangle: Empowering Incident Triage with Multi-Agent. In 2025 40th IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE, 674\u2013686."},{"key":"e_1_3_2_1_48_1","volume-title":"Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering. 38\u201349","author":"Yu Zhaoyang","year":"2024","unstructured":"Zhaoyang Yu, Minghua Ma, Chaoyun Zhang, Si Qin, Yu Kang, Chetan Bansal, Saravan Rajmohan, Yingnong Dang, Changhua Pei, Dan Pei, et al. 2024. Monitorassistant: Simplifying cloud service monitoring via large language models. In Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering. 38\u201349."},{"key":"e_1_3_2_1_49_1","volume-title":"A Survey of AIOps in the Era of Large Language Models. Comput. Surveys","author":"Zhang Lingzhe","year":"2025","unstructured":"Lingzhe Zhang, Tong Jia, Mengxi Jia, Yifan Wu, Aiwei Liu, Yong Yang, Zhonghai Wu, Xuming Hu, Philip Yu, and Ying Li. 2025. A Survey of AIOps in the Era of Large Language Models. Comput. Surveys (2025)."},{"key":"e_1_3_2_1_50_1","volume-title":"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 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18). 519\u2013532."},{"key":"e_1_3_2_1_51_1","volume-title":"Failure diagnosis in microservice systems: A comprehensive survey and analysis. ACM Transactions on Software Engineering and Methodology","author":"Zhang Shenglin","year":"2025","unstructured":"Shenglin Zhang, Sibo Xia, Wenzhao Fan, Binpeng Shi, Xiao Xiong, Zhenyu Zhong, Minghua Ma, Yongqian Sun, and Dan Pei. 2025. Failure diagnosis in microservice systems: A comprehensive survey and analysis. ACM Transactions on Software Engineering and Methodology (2025)."},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 3948\u20133958","author":"Zhang Xu","year":"2021","unstructured":"Xu Zhang, Chao Du, Yifan Li, Yong Xu, Hongyu Zhang, Si Qin, Ze Li, Qingwei Lin, Yingnong Dang, Andrew Zhou, et al. 2021. Halo: Hierarchy-aware fault localization for cloud systems. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 3948\u20133958."},{"key":"e_1_3_2_1_53_1","volume-title":"Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering. 266\u2013277","author":"Zhang Xuchao","year":"2024","unstructured":"Xuchao Zhang, Supriyo Ghosh, Chetan Bansal, Rujia Wang, Minghua Ma, Yu Kang, and Saravan Rajmohan. 2024. Automated root causing of cloud incidents using in-context learning with GPT-4. In Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering. 266\u2013277."},{"key":"e_1_3_2_1_54_1","volume-title":"Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 1253\u20131263","author":"Zhang Xu","year":"2021","unstructured":"Xu Zhang, Yong Xu, Si Qin, Shilin He, Bo Qiao, Ze Li, Hongyu Zhang, Xukun Li, Yingnong Dang, Qingwei Lin, et al. 2021. Onion: identifying incident-indicating logs for cloud systems. In Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 1253\u20131263."}],"event":{"name":"FSE Companion '26: 34th ACM International Conference on the Foundations of Software Engineering","location":"Concordia University Montreal QC Canada","acronym":"FSE Companion '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 34th ACM International Conference on the Foundations of Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3803437.3805241","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:39:30Z","timestamp":1784299170000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3803437.3805241"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":54,"alternative-id":["10.1145\/3803437.3805241","10.1145\/3803437"],"URL":"https:\/\/doi.org\/10.1145\/3803437.3805241","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}