{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T13:18:14Z","timestamp":1763644694370,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,12]]},"DOI":"10.1145\/3725783.3764388","type":"proceedings-article","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:50:12Z","timestamp":1760032212000},"page":"155-167","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Between Promise and Pain: The Reality of Automating Failure Analysis in Microservices with LLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4734-3321","authenticated-orcid":false,"given":"Alessandro","family":"Cornacchia","sequence":"first","affiliation":[{"name":"KAUST, Thuwal, Saudi Arabia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9192-632X","authenticated-orcid":false,"given":"Iliyas","family":"Alabdulaal","sequence":"additional","affiliation":[{"name":"KAUST, Thuwal, Saudi Arabia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8582-3396","authenticated-orcid":false,"given":"Ibraheem","family":"Saghier","sequence":"additional","affiliation":[{"name":"KAUST, Thuwal, Saudi Arabia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6431-0977","authenticated-orcid":false,"given":"Albaraa","family":"Mirdad","sequence":"additional","affiliation":[{"name":"KAUST, Thuwal, Saudi Arabia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4663-396X","authenticated-orcid":false,"given":"Omar","family":"Fayoumi","sequence":"additional","affiliation":[{"name":"KAUST, Thuwal, Saudi Arabia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5051-4283","authenticated-orcid":false,"given":"Marco","family":"Canini","sequence":"additional","affiliation":[{"name":"KAUST, Thuwal, Saudi Arabia"}]}],"member":"320","published-online":{"date-parts":[[2025,10,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Prometheus: Monitoring system & time series database. https:\/\/prometheus.io\/.","author":"Prometheus Authors","year":"2023","unstructured":"Prometheus Authors 2014\u20132025. 2023. Prometheus: Monitoring system & time series database. https:\/\/prometheus.io\/."},{"key":"e_1_3_2_1_2_1","volume-title":"Dheeraj Sreedhar, Praveen Venkateswaran, Merve Unuvar, David Cox, Salim Roukos, Luis Lastras, and Pavan Kapanipathi.","author":"Abdelaziz Ibrahim","year":"2024","unstructured":"Ibrahim Abdelaziz, Kinjal Basu, Mayank Agarwal, Sadhana Kumaravel, Matthew Stallone, Rameswar Panda, Yara Rizk, GP Bhargav, Maxwell Crouse, Chulaka Gunasekara, Shajith Ikbal, Sachin Joshi, Hima Karanam, Vineet Kumar, Asim Munawar, Sumit Neelam, Dinesh Raghu, Udit Sharma, Adriana Meza Soria, Dheeraj Sreedhar, Praveen Venkateswaran, Merve Unuvar, David Cox, Salim Roukos, Luis Lastras, and Pavan Kapanipathi. 2024. Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks. arXiv:2407.00121 [cs.LG] https:\/\/arxiv.org\/abs\/2407.00121"},{"key":"e_1_3_2_1_3_1","volume-title":"Deploying Microservice Based Applications with Kubernetes: Experiments and Lessons Learned. In 2018 IEEE 11th International Conference on Cloud Computing (CLOUD '18)","author":"Vayghan Leila Abdollahi","year":"2018","unstructured":"Leila Abdollahi Vayghan, Mohamed Aymen Saied, Maria Toeroe, and Ferhat Khendek. 2018. Deploying Microservice Based Applications with Kubernetes: Experiments and Lessons Learned. In 2018 IEEE 11th International Conference on Cloud Computing (CLOUD '18)."},{"key":"e_1_3_2_1_4_1","volume-title":"Recommending Root-Cause and Mitigation Steps for Cloud Incidents Using Large Language Models. In International Conference on Software Engineering. 1737\u20131749","author":"Ahmed Toufique","year":"2023","unstructured":"Toufique Ahmed, Supriyo Ghosh, Chetan Bansal, Thomas Zimmermann, Xuchao Zhang, and Saravan Rajmohan. 2023. Recommending Root-Cause and Mitigation Steps for Cloud Incidents Using Large Language Models. In International Conference on Software Engineering. 1737\u20131749."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Sarah Alnegheimish Linh Nguyen Laure Berti-Equille and Kalyan Veeramachaneni. 2024. Large language models can be zero-shot anomaly detectors for time series? arXiv:2405.14755 [cs.LG] https:\/\/arxiv.org\/abs\/2405.14755","DOI":"10.1109\/DSAA61799.2024.10722786"},{"key":"e_1_3_2_1_6_1","volume-title":"Blueprint: A Toolchain for Highly-Reconfigurable Microservice Applications","author":"Anand Vaastav","year":"2023","unstructured":"Vaastav Anand, Deepak Garg, Antoine Kaufmann, and Jonathan Mace. 2023. Blueprint: A Toolchain for Highly-Reconfigurable Microservice Applications. In SOSP. Association for Computing Machinery."},{"key":"e_1_3_2_1_7_1","volume-title":"2025 IEEE\/ACM International Workshop on Cloud Intelligence & AIOps (AIOps). IEEE Computer Society.","author":"Anand Vaastav","year":"2025","unstructured":"Vaastav Anand, Pedro Las-Casas, Rodrigo Fonseca, and Antoine Kaufmann. 2025. Towards Using Llms for Distributed Trace Comparison (Abstract). In 2025 IEEE\/ACM International Workshop on Cloud Intelligence & AIOps (AIOps). IEEE Computer Society."},{"key":"e_1_3_2_1_8_1","volume-title":"Claude: An AI Assistant for Collaborative Reasoning. urlhttps:\/\/www.anthropic.com\/claude.","year":"2025","unstructured":"Anthropic. 2025. Claude: An AI Assistant for Collaborative Reasoning. urlhttps:\/\/www.anthropic.com\/claude."},{"key":"e_1_3_2_1_9_1","unstructured":"The Jaeger Authors. 2023. Jaeger. https:\/\/www.jaegertracing.io\/."},{"key":"e_1_3_2_1_10_1","volume-title":"NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls. arXiv:2409.03797 [cs.AI] https:\/\/arxiv.org\/abs\/2409.03797","author":"Basu Kinjal","year":"2025","unstructured":"Kinjal Basu, Ibrahim Abdelaziz, Kiran Kate, Mayank Agarwal, Maxwell Crouse, Yara Rizk, Kelsey Bradford, Asim Munawar, Sadhana Kumaravel, Saurabh Goyal, Xin Wang, Luis A. Lastras, and Pavan Kapanipathi. 2025. NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls. arXiv:2409.03797 [cs.AI] https:\/\/arxiv.org\/abs\/2409.03797"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Yinfang Chen Huaibing Xie Minghua Ma Yu Kang Xin Gao Liu Shi Yunjie Cao Xuedong Gao Hao Fan Ming Wen et al. 2023. Empowering Practical Root Cause Analysis by Large Language Models for Cloud Incidents. arXiv preprint arXiv:2305.15778 (2023).","DOI":"10.1145\/3627703.3629553"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629553"},{"key":"e_1_3_2_1_13_1","unstructured":"Microsoft Corporation. 2025. AIOpsLab: GitHub Repository. https:\/\/github.com\/microsoft\/AIOpsLab."},{"key":"e_1_3_2_1_14_1","unstructured":"Manqing Dong Hao Huang and Longbing Cao. 2024. Can LLMs Serve As Time Series Anomaly Detectors? arXiv:2408.03475 [cs.LG] https:\/\/arxiv.org\/abs\/2408.03475"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588195.3595943"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2043556.2043585"},{"key":"e_1_3_2_1_17_1","volume-title":"X-Trace: A Pervasive Network Tracing Framework","author":"Fonseca Rodrigo","unstructured":"Rodrigo Fonseca, George Porter, Randy H. Katz, and Scott Shenker. 2007. X-Trace: A Pervasive Network Tracing Framework. In USENIX NSDI. USENIX Association."},{"key":"e_1_3_2_1_18_1","volume-title":"Sage: practical and scalable ML-driven performance debugging in microservices (ASPLOS '21)","author":"Gan Yu","unstructured":"Yu Gan, Mingyu Liang, Sundar Dev, David Lo, and Christina Delimitrou. 2021. Sage: practical and scalable ML-driven performance debugging in microservices (ASPLOS '21). Association for Computing Machinery, 135\u2013151."},{"key":"e_1_3_2_1_19_1","volume-title":"ACM Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS '19)","author":"Gan Yu","unstructured":"Yu Gan, Yanqi Zhang, Dailun Cheng, Ankitha Shetty, Priyal Rathi, Nayan Katarki, Ariana Bruno, Justin Hu, Brian Ritchken, Brendon Jackson, Kelvin Hu, Meghna Pancholi, Yuan He, Brett Clancy, Chris Colen, Fukang Wen, Catherine Leung, Siyuan Wang, Leon Zaruvinsky, Mateo Espinosa, Rick Lin, Zhongling Liu, Jake Padilla, and Christina Delimitrou. 2019. An Open-Source Benchmark Suite for Microservices and Their Hardware-Software Implications for Cloud & Edge Systems. In ACM Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS '19). Association for Computing Machinery."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304004"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.2307\/1912791"},{"key":"e_1_3_2_1_22_1","unstructured":"Wei Guan Jian Cao Shiyou Qian Jianqi Gao and Chun Ouyang. 2025. LogLLM: Log-based Anomaly Detection Using Large Language Models. arXiv:2411.08561 [cs.SE] https:\/\/arxiv.org\/abs\/2411.08561"},{"key":"e_1_3_2_1_23_1","unstructured":"Saurabh Jha Rohan Arora Yuji Watanabe Takumi Yanagawa Yinfang Chen Jackson Clark Bhavya Bhavya Mudit Verma Harshit Kumar Hirokuni Kitahara Noah Zheutlin Saki Takano Divya Pathak Felix George Xinbo Wu Bekir O. Turkkan Gerard Vanloo Michael Nidd Ting Dai Oishik Chatterjee Pranjal Gupta Suranjana Samanta Pooja Aggarwal Rong Lee Pavankumar Murali Jae wook Ahn Debanjana Kar Ameet Rahane Carlos Fonseca Amit Paradkar Yu Deng Pratibha Moogi Prateeti Mohapatra Naoki Abe Chandrasekhar Narayanaswami Tianyin Xu Lav R. Varshney Ruchi Mahindru Anca Sailer Laura Shwartz Daby Sow Nicholas C. M. Fuller and Ruchir Puri. 2025. ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks. arXiv:2502.05352 [cs.AI] https:\/\/arxiv.org\/abs\/2502.05352"},{"key":"e_1_3_2_1_24_1","volume-title":"Xpert: Empowering Incident Management with Query Recommendations via Large Language Models. arXiv:2312.11988 [cs.SE] https:\/\/arxiv.org\/abs\/2312.11988","author":"Jiang Yuxuan","year":"2023","unstructured":"Yuxuan Jiang, Chaoyun Zhang, Shilin He, Zhihao Yang, Minghua Ma, Si Qin, Yu Kang, Yingnong Dang, Saravan Rajmohan, Qingwei Lin, and Dongmei Zhang. 2023. Xpert: Empowering Incident Management with Query Recommendations via Large Language Models. arXiv:2312.11988 [cs.SE] https:\/\/arxiv.org\/abs\/2312.11988"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639081"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3613891"},{"key":"e_1_3_2_1_27_1","unstructured":"Alex Karpenko Alexander Wei Allison Tam Ananya Kumar Andre Saraiva Andrew Kondrich Andrey Mishchenko Ashvin Nair Behrooz Ghorbani Bohan Zhang Brandon McKinzie Brydon Eastman Chak Ming Li Chris Koch Dan Roberts David Dohan David Mely Dimitris Tsipras Enoch Cheung Eric Wallace Hadi Salman Haiming Bao Hessam Bagherinezhad Ilya Kostrikov Jiacheng Feng John Rizzo Karina Nguyen Kevin Lu Kevin Stone Lorenz Kuhn Mason Meyer Mikhail Pavlov Nat McAleese Oleg Boiko Oleg Murk Peter Zhokhov Randall Lin Raz Gaon Rhythm Garg Roshan James Rui Shu Scott McKinney Shibani Santurkar Suchir Balaji Taylor Gordon Thomas Dimson and Weiyi Zheng. 2025. Learning to reason with LLMs. https:\/\/openai.com\/index\/learning-to-reason-with-llms\/."},{"key":"e_1_3_2_1_28_1","volume-title":"International Conference on Learning Representations (ICLR '24)","author":"Khattab Omar","year":"2024","unstructured":"Omar Khattab, Arnav Singhvi, Paridhi Maheshwari, Zhiyuan Zhang, Keshav Santhanam, Sri Vardhamanan, Saiful Haq, Ashutosh Sharma, Thomas T. Joshi, Hanna Moazam, Heather Miller, Matei Zaharia, and Christopher Potts. 2024. DSPy: Compiling Declarative Language Model Calls into State-of-the-Art Pipelines. In International Conference on Learning Representations (ICLR '24). OpenReview.net."},{"key":"e_1_3_2_1_29_1","unstructured":"Myunghwan Kim Roshan Sumbaly and Sam Shah. 2013. Root Cause Detection in a Service-Oriented Architecture. SIGMETRICS Perform. Eval. Rev. (2013)."},{"key":"e_1_3_2_1_30_1","volume-title":"Grafana Labs Observability Survey","author":"Labs Grafana","year":"2023","unstructured":"Grafana Labs. 2023. Grafana Labs Observability Survey 2023. https:\/\/grafana.com\/about\/press\/2023\/03\/08\/grafana-labs-observability-survey-2023-finds-centralization-saves-time-and-money-for-an-industry-plagued-by-tool-and-data-source-overload\/."},{"key":"e_1_3_2_1_31_1","first-page":"1","article-title":"LLexus: an AI agent system for incident management","volume":"58","author":"Las-Casas Pedro","year":"2024","unstructured":"Pedro Las-Casas, Alok Gautum Kumbhare, Rodrigo Fonseca, and Sharad Agarwal. 2024. LLexus: an AI agent system for incident management. SIGOPS Oper. Syst. Rev. 58, 1 (Aug. 2024).","journal-title":"SIGOPS Oper. Syst. Rev."},{"key":"e_1_3_2_1_32_1","volume-title":"Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem.","author":"Li Guohao","year":"2023","unstructured":"Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023. CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society. In NeurIPS 2023. Curran Associates Inc."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/IWQOS52092.2021.9521340"},{"key":"e_1_3_2_1_34_1","unstructured":"Jun Liu Chaoyun Zhang Jiaxu Qian Minghua Ma Si Qin Chetan Bansal Qingwei Lin Saravan Rajmohan and Dongmei Zhang. 2024. Large Language Models can Deliver Accurate and Interpretable Time Series Anomaly Detection. arXiv:2405.15370 [cs.CL] https:\/\/arxiv.org\/abs\/2405.15370"},{"key":"e_1_3_2_1_35_1","unstructured":"Yuhe Liu Changhua Pei Longlong Xu Bohan Chen Mingze Sun Zhirui Zhang Yongqian Sun Shenglin Zhang Kun Wang Haiming Zhang Jianhui Li Gaogang Xie Xidao Wen Xiaohui Nie Minghua Ma and Dan Pei. 2024. OpsEval: A Comprehensive IT Operations Benchmark Suite for Large Language Models. arXiv:2310.07637 [cs.AI] https:\/\/arxiv.org\/abs\/2310.07637"},{"key":"e_1_3_2_1_36_1","unstructured":"Meta. 2025. The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation. urlhttps:\/\/ai.meta.com\/blog\/llama-4-multimodal-intelligence\/."},{"key":"e_1_3_2_1_37_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. urlhttps:\/\/cdn.openai.com\/papers\/gpt-4.pdf."},{"key":"e_1_3_2_1_38_1","unstructured":"OpenAI. 2025. OpenAI Models. https:\/\/platform.openai.com\/docs\/models."},{"key":"e_1_3_2_1_39_1","first-page":"1","article-title":"k-Shape","volume":"45","author":"Paparrizos John","year":"2016","unstructured":"John Paparrizos and Luis Gravano. 2016. k-Shape: Efficient and Accurate Clustering of Time Series. SIGMOD Rec. 45, 1 (June 2016).","journal-title":"Efficient and Accurate Clustering of Time Series. SIGMOD Rec."},{"key":"e_1_3_2_1_40_1","unstructured":"Austin Parker. 2025. MCP Easy as 1-2-3? urlhttps:\/\/www.honeycomb.io\/blog\/mcp-easy-as-1-2-3?utm_source=chatgpt.com."},{"key":"e_1_3_2_1_41_1","volume-title":"RCAEval: A Benchmark for Root Cause Analysis of Microservice Systems with Telemetry Data. In The 2025 ACM Web Conference (WWW).","author":"Pham Luan","year":"2025","unstructured":"Luan Pham, Hongyu Zhang, Huong Ha, Flora Salim, and Xiuzhen Zhang. 2025. RCAEval: A Benchmark for Root Cause Analysis of Microservice Systems with Telemetry Data. In The 2025 ACM Web Conference (WWW)."},{"key":"e_1_3_2_1_42_1","volume-title":"Exploring LLM-Based Agents for Root Cause Analysis","author":"Roy Devjeet","unstructured":"Devjeet Roy, Xuchao Zhang, Rashi Bhave, Chetan Bansal, Pedro Las-Casas, Rodrigo Fonseca, and Saravan Rajmohan. 2024. Exploring LLM-Based Agents for Root Cause Analysis. In ACM FSE. Association for Computing Machinery."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Keshav Santhanam Omar Khattab Jon Saad-Falcon Christopher Potts and Matei Zaharia. 2022. ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction. arXiv:2112.01488 [cs.IR] https:\/\/arxiv.org\/abs\/2112.01488","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"e_1_3_2_1_44_1","unstructured":"Vishwanath Seshagiri Siddharth Balyan Vaastav Anand Kaustubh Dhole Ishan Sharma Avani Wildani Jos\u00e9 Cambronero and Andreas Z\u00fcfle. 2024. Chatting with Logs: An exploratory study on Finetuning LLMs for LogQL. arXiv:2412.03612 [cs.DB] https:\/\/arxiv.org\/abs\/2412.03612"},{"key":"e_1_3_2_1_45_1","volume-title":"Building AI Agents for Autonomous Clouds: Challenges and Design Principles. In ACM Symposium on Cloud Computing (SoCC '24)","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, Suman Nath, Chetan Bansal, and Saravan Rajmohan. 2024. Building AI Agents for Autonomous Clouds: Challenges and Design Principles. In ACM Symposium on Cloud Computing (SoCC '24). Association for Computing Machinery."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER64311.2025.00082"},{"key":"e_1_3_2_1_47_1","volume-title":"ACM\/IFIP\/USENIX Middleware Conference. 14\u201327","author":"Thalheim J\u00f6rg","year":"2017","unstructured":"J\u00f6rg Thalheim, Antonio Rodrigues, Istemi Ekin Akkus, Pramod Bhatotia, Ruichuan Chen, Bimal Viswanath, Lei Jiao, and Christof Fetzer. 2017. Sieve: Actionable insights from monitored metrics in distributed systems. In ACM\/IFIP\/USENIX Middleware Conference. 14\u201327."},{"key":"e_1_3_2_1_48_1","unstructured":"Santiago Valdarrama. 2024. X Post. https:\/\/x.com\/svpino\/status\/1841461406081626296?s=46&t=1-9-9RQXPlSV9HwI8l0BGg."},{"key":"e_1_3_2_1_49_1","unstructured":"Xingyao Wang Yangyi Chen Lifan Yuan Yizhe Zhang Yunzhu Li Hao Peng and Ji Heng. 2024. CodeAct: Your LLM Agent Acts Better when Generating Code. In ICML. https:\/\/arxiv.org\/abs\/2402.01030"},{"key":"e_1_3_2_1_50_1","volume-title":"ICML. JMLR.org, Article","author":"Wang Xingyao","year":"2054","unstructured":"Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, and Heng Ji. 2024. Executable code actions elicit better LLM agents. In ICML. JMLR.org, Article 2054."},{"key":"e_1_3_2_1_51_1","volume-title":"ACM Conference on Information and Knowledge Management (CIKM '24)","author":"Wang Zefan","year":"2024","unstructured":"Zefan Wang, Zichuan Liu, Yingying Zhang, Aoxiao Zhong, Jihong Wang, Fengbin Yin, Lunting Fan, Lingfei Wu, and Qingsong Wen. 2024. RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models. In ACM Conference on Information and Knowledge Management (CIKM '24). ACM."},{"key":"e_1_3_2_1_52_1","volume-title":"Quoc V. Le, and Denny Zhou.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. In NeurIPS. Curran Associates Inc."},{"key":"e_1_3_2_1_53_1","volume-title":"MicroRCA: Root cause localization of performance issues in microservices","author":"Wu Li","unstructured":"Li Wu, Johan Tordsson, Erik Elmroth, and Odej Kao. 2020. MicroRCA: Root cause localization of performance issues in microservices. In IEEE NOMS."},{"key":"e_1_3_2_1_54_1","volume-title":"Ryen W White, Doug Burger, and Chi Wang.","author":"Wu Qingyun","year":"2023","unstructured":"Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, Ahmed Hassan Awadallah, Ryen W White, Doug Burger, and Chi Wang. 2023. AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation. arXiv:2308.08155 [cs.AI] https:\/\/arxiv.org\/abs\/2308.08155"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"crossref","unstructured":"Zhe Xie Zeyan Li Xiao He Longlong Xu Xidao Wen Tieying Zhang Jianjun Chen Rui Shi and Dan Pei. 2025. ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning. arXiv:2412.03104 [cs.AI] https:\/\/arxiv.org\/abs\/2412.03104","DOI":"10.14778\/3742728.3742735"},{"key":"e_1_3_2_1_56_1","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. arXiv:2210.03629"},{"key":"e_1_3_2_1_57_1","volume-title":"ACM Web Conference","author":"Yu Guangba","year":"2021","unstructured":"Guangba Yu, Pengfei Chen, Hongyang Chen, Zijie Guan, Zicheng Huang, Linxiao Jing, Tianjun Weng, Xinmeng Sun, and Xiaoyun Li. 2021. Microrank: End-to-end latency issue localization with extended spectrum analysis in microservice environments. In ACM Web Conference 2021. 3087\u20133098."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3663529.3663826"},{"key":"e_1_3_2_1_59_1","volume-title":"SherLog: Error Diagnosis by Connecting Clues from Run-Time Logs","author":"Yuan Ding","unstructured":"Ding Yuan, Haohui Mai, Weiwei Xiong, Lin Tan, Yuanyuan Zhou, and Shankar Pasupathy. 2010. SherLog: Error Diagnosis by Connecting Clues from Run-Time Logs. In ACM ASPLOS. Association for Computing Machinery."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510180"},{"key":"e_1_3_2_1_61_1","unstructured":"Chenxi Zhang Bicheng Zhang Dingyu Yang Xin Peng Miao Chen Senyu Xie Gang Chen Wei Bi and Wei Li. 2025. PromAssistant: Leveraging Large Language Models for Text-to-PromQL. arXiv:2503.03114 [cs.SE] https:\/\/arxiv.org\/abs\/2503.03114"},{"key":"e_1_3_2_1_62_1","volume-title":"The Benefit of Hindsight: Tracing Edge-Cases in Distributed Systems","author":"Zhang Lei","unstructured":"Lei Zhang, Zhiqiang Xie, Vaastav Anand, Ymir Vigfusson, and Jonathan Mace. 2023. The Benefit of Hindsight: Tracing Edge-Cases in Distributed Systems. In USENIX NSDI. USENIX Association."},{"key":"e_1_3_2_1_63_1","volume-title":"Latent error prediction and fault localization for microservice applications by learning from system trace logs","author":"Zhou Xiang","unstructured":"Xiang Zhou, Xin Peng, Tao Xie, Jun Sun, Chao Ji, Dewei Liu, Qilin Xiang, and Chuan He. 2019. Latent error prediction and fault localization for microservice applications by learning from system trace logs. In ACM ESEC\/FSE. Association for Computing Machinery."}],"event":{"name":"APSys '25: 16th ACM SIGOPS Asia-Pacific Workshop on Systems","location":"Lotte Hotel World, Emerald Hall Seoul Republic of Korea","acronym":"APSys '25","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 16th ACM SIGOPS Asia-Pacific Workshop on Systems"],"original-title":[],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:50:30Z","timestamp":1760032230000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725783.3764388"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,11]]},"references-count":63,"alternative-id":["10.1145\/3725783.3764388","10.1145\/3725783"],"URL":"https:\/\/doi.org\/10.1145\/3725783.3764388","relation":{},"subject":[],"published":{"date-parts":[[2025,10,11]]},"assertion":[{"value":"2025-10-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}