{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:21:18Z","timestamp":1783009278332,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":91,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62325205"],"award-info":[{"award-number":["62325205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Municipal Science and Technology Project","award":["Z241100004224023"],"award-info":[{"award-number":["Z241100004224023"]}]},{"name":"National Natural Science Fund for the Excellent Young Scientists Fund Program (Overseas)","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1145\/3718958.3750505","type":"proceedings-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T16:54:11Z","timestamp":1756313651000},"page":"496-511","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Towards LLM-Based Failure Localization in Production-Scale Networks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6347-3233","authenticated-orcid":false,"given":"Chenxu","family":"Wang","sequence":"first","affiliation":[{"name":"Nanjing University, Nanjing, Jiangsu, China"},{"name":"Alibaba Cloud, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3551-4074","authenticated-orcid":false,"given":"Xumiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Sunnyvale, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0902-4262","authenticated-orcid":false,"given":"Runwei","family":"Lu","sequence":"additional","affiliation":[{"name":"New York University Shanghai, Shanghai, China"},{"name":"Alibaba Cloud, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1811-4713","authenticated-orcid":false,"given":"Xianshang","family":"Lin","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1755-9444","authenticated-orcid":false,"given":"Xuan","family":"Zeng","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1993-9573","authenticated-orcid":false,"given":"Xinlei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Sunnyvale, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8575-5339","authenticated-orcid":false,"given":"Zhe","family":"An","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4906-1400","authenticated-orcid":false,"given":"Gongwei","family":"Wu","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3548-2030","authenticated-orcid":false,"given":"Jiaqi","family":"Gao","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Bellevue, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2710-7628","authenticated-orcid":false,"given":"Chen","family":"Tian","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6934-1685","authenticated-orcid":false,"given":"Guihai","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4933-0276","authenticated-orcid":false,"given":"Guyue","family":"Liu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7216-5592","authenticated-orcid":false,"given":"Yuhong","family":"Liao","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6382-4793","authenticated-orcid":false,"given":"Tao","family":"Lin","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Sunnyvale, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7272-8143","authenticated-orcid":false,"given":"Dennis","family":"Cai","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Sunnyvale, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4352-7497","authenticated-orcid":false,"given":"Ennan","family":"Zhai","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2023. IT outages cost companies up to $1M per hour: report. https:\/\/www.ciodive.com\/news\/IT-outage-cost-report-new-relic\/696359\/."},{"key":"e_1_3_2_1_2_1","unstructured":"2024. Anthropic - Introducing Claude 3.5 Sonnet. https:\/\/www.anthropic.com\/news\/claude-3-5-sonnet."},{"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","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Agarwal Anup","year":"2022","unstructured":"Anup Agarwal, Zaoxing Liu, and Srinivasan Seshan. 2022. {HeteroSketch}: Coordinating network-wide monitoring in heterogeneous and dynamic networks. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). 719\u2013741."},{"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","volume-title":"ACM CoNEXT","author":"Ajay MAHIMKAR","year":"2008","unstructured":"MAHIMKAR Ajay. 2008. Troubleshooting Chronic Conditions in Large IP Networks. ACM CoNEXT, December 2008, Madrid, Spain (2008)."},{"key":"e_1_3_2_1_7_1","volume-title":"15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18)","author":"Arzani Behnaz","year":"2018","unstructured":"Behnaz Arzani, Selim Ciraci, Luiz Chamon, Yibo Zhu, Hongqiang Harry Liu, Jitu Padhye, Boon Thau Loo, and Geoff Outhred. 2018. 007: Democratically finding the cause of packet drops. In 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18). 419\u2013435."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934884"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1282427.1282383"},{"key":"e_1_3_2_1_10_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the Annual conference of the ACM Special Interest Group on Data Communication on the applications, technologies, architectures, and protocols for computer communication. 662\u2013680","author":"Basat Ran Ben","year":"2020","unstructured":"Ran Ben Basat, Sivaramakrishnan Ramanathan, Yuliang Li, Gianni Antichi, Minian Yu, and Michael Mitzenmacher. 2020. PINT: Probabilistic in-band network telemetry. In Proceedings of the Annual conference of the ACM Special Interest Group on Data Communication on the applications, technologies, architectures, and protocols for computer communication. 662\u2013680."},{"key":"e_1_3_2_1_12_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877\u20131901."},{"key":"e_1_3_2_1_13_1","unstructured":"Mert Cemri Melissa Z Pan Shuyi Yang Lakshya A Agrawal Bhavya Chopra Rishabh Tiwari Kurt Keutzer Aditya Parameswaran Dan Klein Kannan Ramchandran et al. 2025. Why do multi-agent llm systems fail? arXiv preprint arXiv:2503.13657 (2025)."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 2016 ACM SIGCOMM Conference. 115\u2013128","author":"Chen Ang","year":"2016","unstructured":"Ang Chen, Yang Wu, Andreas Haeberlen, Wenchao Zhou, and Boon Thau Loo. 2016. The good, the bad, and the differences: Better network diagnostics with differential provenance. In Proceedings of the 2016 ACM SIGCOMM Conference. 115\u2013128."},{"key":"e_1_3_2_1_15_1","volume-title":"Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors in agents. arXiv preprint arXiv:2308.10848","author":"Chen Weize","year":"2023","unstructured":"Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Chen Qian, Chi-Min Chan, Yujia Qin, Yaxi Lu, Ruobing Xie, et al. 2023. Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors in agents. arXiv preprint arXiv:2308.10848 (2023)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629553"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446700"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the Annual conference of the ACM Special Interest Group on Data Communication on the applications, technologies, architectures, and protocols for computer communication. 253\u2013269","author":"Gao Jiaqi","year":"2020","unstructured":"Jiaqi Gao, Nofel Yaseen, Robert MacDavid, Felipe Vieira Frujeri, Vincent Liu, Ricardo Bianchini, Ramaswamy Aditya, Xiaohang Wang, Henry Lee, David Maltz, et al. 2020. Scouts: Improving the diagnosis process through domain-customized incident routing. In Proceedings of the Annual conference of the ACM Special Interest Group on Data Communication on the applications, technologies, architectures, and protocols for computer communication. 253\u2013269."},{"key":"e_1_3_2_1_19_1","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Gao Kaihui","year":"2022","unstructured":"Kaihui Gao, Chen Sun, Shuai Wang, Dan Li, Yu Zhou, Hongqiang Harry Liu, Lingjun Zhu, and Ming Zhang. 2022. Buffer-based end-to-end request event monitoring in the cloud. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). 829\u2013843."},{"key":"e_1_3_2_1_20_1","volume-title":"16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19)","author":"Geng Yilong","year":"2019","unstructured":"Yilong Geng, Shiyu Liu, Zi Yin, Ashish Naik, Balaji Prabhakar, Mendel Rosenblum, and Amin Vahdat. 2019. {SIMON}: A simple and scalable method for sensing, inference and measurement in data center networks. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19). 549\u2013564."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3050220.3050228"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the 2015 ACM Conference on Special Interest Group on Data Communication. 139\u2013152","author":"Guo Chuanxiong","year":"2015","unstructured":"Chuanxiong Guo, Lihua Yuan, Dong Xiang, Yingnong Dang, Ray Huang, Dave Maltz, Zhaoyi Liu, Vin Wang, Bin Pang, Hua Chen, et al. 2015. Pingmesh: A large-scale system for data center network latency measurement and analysis. In Proceedings of the 2015 ACM Conference on Special Interest Group on Data Communication. 139\u2013152."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230555"},{"key":"e_1_3_2_1_24_1","volume-title":"11th USENIX Symposium on Networked Systems Design and Implementation (NSDI 14)","author":"Handigol Nikhil","year":"2014","unstructured":"Nikhil Handigol, Brandon Heller, Vimalkumar Jeyakumar, David Mazi\u00e8res, and Nick McKeown. 2014. I know what your packet did last hop: Using packet histories to troubleshoot networks. In 11th USENIX Symposium on Networked Systems Design and Implementation (NSDI 14). 71\u201385."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3185467.3185476"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the ACM on Networking 1, CoNEXT1","author":"Harsh Vipul","year":"2023","unstructured":"Vipul Harsh, Tong Meng, Kapil Agrawal, and Philip Brighten Godfrey. 2023. Flock: Accurate network fault localization at scale. Proceedings of the ACM on Networking 1, CoNEXT1 (2023), 1\u201322."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604877"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. 1689\u20131698","author":"Herodotou Herodotos","year":"2014","unstructured":"Herodotos Herodotou, Bolin Ding, Shobana Balakrishnan, Geoff Outhred, and Percy Fitter. 2014. Scalable near real-time failure localization of data center networks. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. 1689\u20131698."},{"key":"e_1_3_2_1_29_1","volume-title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework. In The Twelfth International Conference on Learning Representations.","author":"Hong Sirui","year":"2024","unstructured":"Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, and J\u00fcrgen Schmidhuber. 2024. MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication. 576\u2013590","author":"Huang Qun","year":"2018","unstructured":"Qun Huang, Patrick PC Lee, and Yungang Bao. 2018. Sketchlearn: Relieving user burdens in approximate measurement with automated statistical inference. In Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication. 576\u2013590."},{"key":"e_1_3_2_1_31_1","volume-title":"18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","author":"Huang Qun","year":"2021","unstructured":"Qun Huang, Siyuan Sheng, Xiang Chen, Yungang Bao, Rui Zhang, Yanwei Xu, and Gong Zhang. 2021. Toward {Nearly-Zero-Error} sketching via compressive sensing. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21). 1027\u20131044."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405877"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3613891"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the ACM SIGCOMM 2009 conference on Data communication. 243\u2013254","author":"Kandula Srikanth","year":"2009","unstructured":"Srikanth Kandula, Ratul Mahajan, Patrick Verkaik, Sharad Agarwal, Jitendra Padhye, and Paramvir Bahl. 2009. Detailed diagnosis in enterprise networks. In Proceedings of the ACM SIGCOMM 2009 conference on Data communication. 243\u2013254."},{"key":"e_1_3_2_1_35_1","volume-title":"18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","author":"Kannan Pravein Govindan","year":"2021","unstructured":"Pravein Govindan Kannan, Nishant Budhdev, Raj Joshi, and Mun Choon Chan. 2021. Debugging transient faults in data centers using synchronized network-wide packet histories. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21). 253\u2013268."},{"key":"e_1_3_2_1_36_1","volume-title":"IEEE INFOCOM 2007-26th IEEE International Conference on Computer Communications. IEEE, 2180\u20132188","author":"Kompella Ramana Rao","year":"2007","unstructured":"Ramana Rao Kompella, Jennifer Yates, Albert Greenberg, and Alex C Snoeren. 2007. Detection and localization of network black holes. In IEEE INFOCOM 2007-26th IEEE International Conference on Computer Communications. IEEE, 2180\u20132188."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2009.37"},{"key":"e_1_3_2_1_38_1","unstructured":"Petr Lapukhov and Aijay Adams. 2016. NetNORAD: Troubleshooting networks via end-to-end probing. https:\/\/engineering.fb.com\/2016\/02\/18\/core-infra\/netnorad-troubleshooting-networks-via-end-to-end-probing\/."},{"key":"e_1_3_2_1_39_1","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis Patrick","year":"2020","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.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_40_1","first-page":"51991","article-title":"Camel: Communicative agents for\" mind\" exploration of large language model society","volume":"36","author":"Li Guohao","year":"2023","unstructured":"Guohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023. Camel: Communicative agents for\" mind\" exploration of large language model society. Advances in Neural Information Processing Systems 36 (2023), 51991\u201352008.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_41_1","volume-title":"13th USENIX symposium on networked systems design and implementation (NSDI 16)","author":"Li Yuliang","year":"2016","unstructured":"Yuliang Li, Rui Miao, Changhoon Kim, and Minlan Yu. 2016. {FlowRadar}: A better {NetFlow} for data centers. In 13th USENIX symposium on networked systems design and implementation (NSDI 16). 311\u2013324."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2999572.2999609"},{"key":"e_1_3_2_1_43_1","volume-title":"17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20)","author":"Li Ze","year":"2020","unstructured":"Ze Li, Qian Cheng, Ken Hsieh, Yingnong Dang, Peng Huang, Pankaj Singh, Xinsheng Yang, Qingwei Lin, Youjiang Wu, Sebastien Levy, et al. 2020. Gandalf: An intelligent,{End-To-End} analytics service for safe deployment in {Large-Scale} cloud infrastructure. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20). 389\u2013402."},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of the ACM SIGCOMM 2024 Conference. 554\u2013567","author":"Liu Kefei","year":"2024","unstructured":"Kefei Liu, Zhuo Jiang, Jiao Zhang, Shixian Guo, Xuan Zhang, Yangyang Bai, Yongbin Dong, Feng Luo, Zhang Zhang, Lei Wang, et al. 2024. R-Pingmesh: A Service-Aware RoCE Network Monitoring and Diagnostic System. In Proceedings of the ACM SIGCOMM 2024 Conference. 554\u2013567."},{"key":"e_1_3_2_1_45_1","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Liu Kefei","year":"2023","unstructured":"Kefei Liu, Zhuo Jiang, Jiao Zhang, Haoran Wei, Xiaolong Zhong, Lizhuang Tan, Tian Pan, and Tao Huang. 2023. Hostping: Diagnosing intra-host network bottlenecks in {RDMA} servers. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 15\u201329."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342076"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934906"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/1594977.1592596"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/1851182.1851219"},{"key":"e_1_3_2_1_50_1","volume-title":"17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20)","author":"Mehta Sonu","year":"2020","unstructured":"Sonu Mehta, Ranjita Bhagwan, Rahul Kumar, Chetan Bansal, Chandra Maddila, Balasubramanyan Ashok, Sumit Asthana, Christian Bird, and Aditya Kumar. 2020. Rex: Preventing bugs and misconfiguration in large services using correlated change analysis. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20). 435\u2013448."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934879"},{"key":"e_1_3_2_1_52_1","volume-title":"22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25)","author":"Namyar Pooria","year":"2025","unstructured":"Pooria Namyar, Arvin Ghavidel, Daniel Crankshaw, Daniel S Berger, Kevin Hsieh, Srikanth Kandula, Ramesh Govindan, and Behnaz Arzani. 2025. Enhancing Network Failure Mitigation with {Performance-Aware} Ranking. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25). 335\u2013357."},{"key":"e_1_3_2_1_53_1","volume-title":"2017 USENIX Annual Technical Conference (USENIX ATC 17)","author":"Peng Yanghua","year":"2017","unstructured":"Yanghua Peng, Ji Yang, Chuan Wu, Chuanxiong Guo, Chengchen Hu, and Zongpeng Li. 2017. {deTector}: a topology-aware monitoring system for data center networks. In 2017 USENIX Annual Technical Conference (USENIX ATC 17). 55\u201368."},{"key":"e_1_3_2_1_54_1","volume-title":"Proceedings of the 10th ACM SIGCOMM conference on Internet measurement. 472\u2013484","author":"Qiu Tongqing","year":"2010","unstructured":"Tongqing Qiu, Zihui Ge, Dan Pei, Jia Wang, and Jun Xu. 2010. What happened in my network: mining network events from router syslogs. In Proceedings of the 10th ACM SIGCOMM conference on Internet measurement. 472\u2013484."},{"key":"e_1_3_2_1_55_1","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Roy Arjun","year":"2017","unstructured":"Arjun Roy, Hongyi Zeng, Jasmeet Bagga, and Alex C Snoeren. 2017. Passive realtime datacenter fault detection and localization. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17). 595\u2013612."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3663529.3663841"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604823"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3050220.3063772"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604847"},{"key":"e_1_3_2_1_60_1","volume-title":"12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)","author":"Tammana Praveen","year":"2016","unstructured":"Praveen Tammana, Rachit Agarwal, and Myungjin Lee. 2016. Simplifying datacenter network debugging with {PathDump}. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16). 233\u2013248."},{"key":"e_1_3_2_1_61_1","volume-title":"15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18)","author":"Tammana Praveen","year":"2018","unstructured":"Praveen Tammana, Rachit Agarwal, and Myungjin Lee. 2018. Distributed network monitoring and debugging with {SwitchPointer}. In 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18). 453\u2013456."},{"key":"e_1_3_2_1_62_1","volume-title":"16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19)","author":"Tan Cheng","year":"2019","unstructured":"Cheng Tan, Ze Jin, Chuanxiong Guo, Tianrong Zhang, Haitao Wu, Karl Deng, Dongming Bi, and Dong Xiang. 2019. {NetBouncer}: Active device and link failure localization in data center networks. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19). 599\u2013614."},{"key":"e_1_3_2_1_63_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Yonghui Wu Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_64_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_65_1","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Wang Haopei","year":"2024","unstructured":"Haopei Wang, Anubhavnidhi Abhashkumar, Changyu Lin, Tianrong Zhang, Xiaoming Gu, Ning Ma, Chang Wu, Songlin Liu, Wei Zhou, Yongbin Dong, et al. 2024. {NetAssistant}: Dialogue Based Network Diagnosis in Data Center Networks. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). 2011\u20132024."},{"key":"e_1_3_2_1_66_1","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Wang Weitao","year":"2022","unstructured":"Weitao Wang, Xinyu Crystal Wu, Praveen Tammana, Ang Chen, and TS Eugene Ng. 2022. Closed-loop network performance monitoring and diagnosis with {SpiderMon}. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). 267\u2013285."},{"key":"e_1_3_2_1_67_1","volume-title":"Aakanksha Chowdhery, and Denny Zhou.","author":"Wang Xuezhi","year":"2022","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171 (2022)."},{"key":"e_1_3_2_1_68_1","volume-title":"2024 USENIX Annual Technical Conference (USENIX ATC 24)","author":"Wang Zhe","year":"2024","unstructured":"Zhe Wang, Huanwu Hu, Linghe Kong, Xinlei Kang, Qiao Xiang, Jingxuan Li, Yang Lu, Zhuo Song, Peihao Yang, Jiejian Wu, et al. 2024. Diagnosing Application-network Anomalies for Millions of {IPs} in Production Clouds. In 2024 USENIX Annual Technical Conference (USENIX ATC 24). 885\u2013899."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3680016"},{"key":"e_1_3_2_1_70_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_71_1","unstructured":"Jerry Wei Jason Wei Yi Tay Dustin Tran Albert Webson Yifeng Lu Xinyun Chen Hanxiao Liu Da Huang Denny Zhou et al. 2023. Larger language models do in-context learning differently. arXiv preprint arXiv:2303.03846 (2023)."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672268"},{"key":"e_1_3_2_1_73_1","volume-title":"First Conference on Language Modeling.","author":"Wu Qingyun","year":"2024","unstructured":"Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, et al. 2024. Autogen: Enabling next-gen LLM applications via multi-agent conversations. In First Conference on Language Modeling."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/2342356.2342438"},{"key":"e_1_3_2_1_75_1","volume-title":"16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19)","author":"Wu Yang","year":"2019","unstructured":"Yang Wu, Ang Chen, and Linh Thi Xuan Phan. 2019. Zeno: Diagnosing performance problems with temporal provenance. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19). 395\u2013420."},{"key":"e_1_3_2_1_76_1","volume-title":"Proceedings of the 6th International COnference. 1\u201312","author":"Yan He","year":"2010","unstructured":"He Yan, Lee Breslau, Zihui Ge, Dan Massey, Dan Pei, and Jennifer Yates. 2010. G-rca: a generic root cause analysis platform for service quality management in large ip networks. In Proceedings of the 6th International COnference. 1\u201312."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230544"},{"key":"e_1_3_2_1_78_1","volume-title":"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_79_1","volume-title":"8th USENIX Symposium on Networked Systems Design and Implementation (NSDI 11)","author":"Yu Minlan","year":"2011","unstructured":"Minlan Yu, Albert Greenberg, Dave Maltz, Jennifer Rexford, Lihua Yuan, Srikanth Kandula, and Changhoon Kim. 2011. Profiling network performance for multi-tier data center applications. In 8th USENIX Symposium on Networked Systems Design and Implementation (NSDI 11)."},{"key":"e_1_3_2_1_80_1","volume-title":"10th USENIX symposium on networked systems design and implementation (NSDI 13)","author":"Yu Minlan","year":"2013","unstructured":"Minlan Yu, Lavanya Jose, and Rui Miao. 2013. Software {Defined}{Traffic} Measurement with {OpenSketch}. In 10th USENIX symposium on networked systems design and implementation (NSDI 13). 29\u201342."},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/3663529.3663826"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/2413176.2413205"},{"key":"e_1_3_2_1_83_1","unstructured":"Hongyi Zeng Ratul Mahajan Nick McKeown George Varghese Lihua Yuan and Ming Zhang. 2015. Measuring and Troubleshooting Large Operational Multipath Networks with Gray Box Testing. Technical Report MSR-TR-2015-55."},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/3663529.3663858"},{"key":"e_1_3_2_1_85_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_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3663529.3663846"},{"key":"e_1_3_2_1_87_1","volume-title":"Proceedings of the ACM SIGCOMM 2024 Conference. 274\u2013290","author":"Zheng Hao","year":"2024","unstructured":"Hao Zheng, Chengyuan Huang, Xiangyu Han, Jiaqi Zheng, Xiaoliang Wang, Chen Tian, Wanchun Dou, and Guihai Chen. 2024. \u03bcMon: Empowering Microsecond-level Network Monitoring with Wavelets. In Proceedings of the ACM SIGCOMM 2024 Conference. 274\u2013290."},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3406214"},{"key":"e_1_3_2_1_89_1","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Zhou Yang","year":"2022","unstructured":"Yang Zhou, Ying Zhang, Minlan Yu, Guangyu Wang, Dexter Cao, Eric Sung, and Starsky Wong. 2022. Evolvable network telemetry at facebook. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). 961\u2013975."},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787483"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098849"}],"event":{"name":"SIGCOMM '25: ACM SIGCOMM 2025 Conference","location":"S\u00e3o Francisco Convent Coimbra Portugal","acronym":"SIGCOMM '25","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the ACM SIGCOMM 2025 Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3718958.3750505","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T16:54:31Z","timestamp":1756313671000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3718958.3750505"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,27]]},"references-count":91,"alternative-id":["10.1145\/3718958.3750505","10.1145\/3718958"],"URL":"https:\/\/doi.org\/10.1145\/3718958.3750505","relation":{},"subject":[],"published":{"date-parts":[[2025,8,27]]},"assertion":[{"value":"2025-08-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}