{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T17:20:28Z","timestamp":1787505628431,"version":"build-2736575974"},"reference-count":33,"publisher":"Association for Computing Machinery (ACM)","issue":"FSE","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFB4505904"],"award-info":[{"award-number":["2024YFB4505904"]}]},{"name":"the National Natural Science Foundation of China under Grant","award":["62272495"],"award-info":[{"award-number":["62272495"]}]},{"name":"the Guangdong Basic and Applied Basic Research Foundation under Grant","award":["2023B1515020054"],"award-info":[{"award-number":["2023B1515020054"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Softw. Eng."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>The dynamics and complexity of cloud-native systems present significant challenges for Root Cause Analysis (RCA). While causality-based RCA methods have shown significant progress in recent years, their practical adoption is fundamentally limited by three intertwined challenges: poor scalability against system complexity, brittle generalization across different system topologies, and inadequate integration of domain knowledge. These limitations create a vicious cycle, hindering the development of robust and efficient RCA solutions. This paper introduces MetaRCA, a generalizable RCA framework for cloud-native systems. MetaRCA first constructs a Meta Causal Graph (MCG) offline, a reusable knowledge base defined at the metadata level. To build the MCG, we propose an evidence-driven algorithm that systematically fuses knowledge from Large Language Models (LLMs), historical fault reports, and observability data. When a fault occurs, MetaRCA performs a lightweight online inference by dynamically instantiating the MCG into a localized graph based on the current context, and then leverages real-time data to weight and prune causal links for precise root cause localization. Evaluated on 252 public and 59 production failures, MetaRCA demonstrates state-of-the-art performance. It surpasses the strongest baseline by 29 percentage points in service-level and 48 percentage points in metric-level accuracy. This performance advantage widens as system complexity increases, with its overhead scaling near-linearly. Crucially, MetaRCA shows robust cross-system generalization, maintaining over 80% accuracy across diverse systems.<\/jats:p>","DOI":"10.1145\/3797069","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:06:14Z","timestamp":1782839174000},"page":"138-159","source":"Crossref","is-referenced-by-count":1,"title":["MetaRCA: A Generalizable Root Cause Analysis Framework for Cloud-Native Systems Powered by Meta Causal Knowledge"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0008-0256-9037","authenticated-orcid":false,"given":"Shuai","family":"Liang","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"},{"name":"China Unicom Software Research Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0003-0972-6900","authenticated-orcid":false,"given":"Pengfei","family":"Chen","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0005-6409-4506","authenticated-orcid":false,"given":"Bozhe","family":"Tian","sequence":"additional","affiliation":[{"name":"China Unicom Software Research Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0008-6580-1470","authenticated-orcid":false,"given":"Gou","family":"Tan","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0001-8208-6420","authenticated-orcid":false,"given":"Maohong","family":"Xu","sequence":"additional","affiliation":[{"name":"China Unicom Software Research Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0008-9926-5899","authenticated-orcid":false,"given":"Youjun","family":"Qu","sequence":"additional","affiliation":[{"name":"China Unicom Software Research Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0001-2024-4585","authenticated-orcid":false,"given":"Yahui","family":"Zhao","sequence":"additional","affiliation":[{"name":"China Unicom Software Research Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0005-5523-3084","authenticated-orcid":false,"given":"Yiduo","family":"Shang","sequence":"additional","affiliation":[{"name":"China Unicom Software Research Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0003-6822-6540","authenticated-orcid":false,"given":"Chongkang","family":"Tan","sequence":"additional","affiliation":[{"name":"Individual Researcher, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"AIOps Organizing Committee. 2022. AIOps 2022 Championship. https:\/\/2.zoppoz.workers.dev:443\/https\/competition.aiops.cn\/. [Accessed: 2025-09-12]."},{"key":"e_1_2_1_2_1","volume-title":"Site Reliability Engineering: How Google Runs Production Systems","author":"Beyer Betsy","unstructured":"Betsy Beyer, Chris Jones, Jennifer Petoff, and Niall Richard Murphy. 2016. Site Reliability Engineering: How Google Runs Production Systems. O'Reilly Media, Inc."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-7552(98)00110-X"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2014.6848128"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629553"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2507.06261"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","unstructured":"DeepSeek-AI Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi Xiaokang Zhang Xingkai Yu Yu Wu Z. F. Wu Zhibin Gou Zhihong Shao Zhuoshu Li Ziyi Gao Aixin Liu Bing Xue Bingxuan Wang Bochao Wu Bei Feng Chengda Lu et al. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. CoRR abs\/2501.12948 (2025). arXiv:2501.12948 doi:10.48550\/ARXIV.2501.12948 10.48550\/ARXIV.2501.12948","DOI":"10.48550\/ARXIV.2501.12948"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/0165-1889(80)90069-X"},{"key":"e_1_2_1_9_1","volume-title":"Software Engineering at Google. arXiv preprint arXiv:1702.01715","author":"Henderson Fergus","year":"2017","unstructured":"Fergus Henderson. 2017. Software Engineering at Google. arXiv preprint arXiv:1702.01715 (2017). arXiv:1702.01715 https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/1702.01715"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.3390\/E25060884"},{"key":"e_1_2_1_11_1","volume-title":"Amit Sharma, and Chenhao Tan.","author":"Kiciman Emre","year":"2024","unstructured":"Emre Kiciman, Robert Osazuwa Ness, Amit Sharma, and Chenhao Tan. 2024. Causal Reasoning and Large Language Models: Opening a New Frontier for Causality. Trans. Mach. Learn. Res. 2024 (2024). https:\/\/2.zoppoz.workers.dev:443\/https\/openreview.net\/forum? id=mqoxLkX210"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539041"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-03596-9_1"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP52600.2021.00043"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380111"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/IWQOS49365.2020.9213058"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1098\/rspl.1895.0041"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3691620.3695065"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3715290"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.3390\/app10062166"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aau4996"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP55303.2022.9793994"},{"key":"e_1_2_1_24_1","volume-title":"Prediction, and Search","author":"Spirtes Peter","unstructured":"Peter Spirtes, Clark Glymour, and Richard Scheines. 2000. Causation, Prediction, and Search, Second Edition. MIT Press."},{"key":"e_1_2_1_25_1","unstructured":"Paul Tibbitt. 2024. The Strategic Advantage and Barriers of Tech Stack Consolidation. https:\/\/2.zoppoz.workers.dev:443\/https\/www.forbes.com\/ councils\/forbesbusinesscouncil\/2024\/11\/07\/the-strategic-advantage-of-tech-stack-consolidation-and-how-toovercome-the-barriers\/. [Accessed: 2025-09-12]."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE51524.2021.9678708"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2018.00076"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2407.08694"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.JSS.2023.111724"},{"key":"e_1_2_1_31_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR). OpenReview.net. https:\/\/2.zoppoz.workers.dev:443\/https\/openreview. net\/forum?id=M4qNIzQYpd","author":"Xu Junjielong","year":"2025","unstructured":"Junjielong Xu, Qinan Zhang, Zhiqing Zhong, Shilin He, Chaoyun Zhang, Qingwei Lin, Dan Pei, Pinjia He, Dongmei Zhang, and Qi Zhang. 2025. OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?. In Proceedings of the International Conference on Learning Representations (ICLR). OpenReview.net. https:\/\/2.zoppoz.workers.dev:443\/https\/openreview. net\/forum?id=M4qNIzQYpd"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3663529.3663827"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2407.01710"}],"container-title":["Proceedings of the ACM on Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/pdf\/10.1145\/3797069","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:08:36Z","timestamp":1782842916000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/10.1145\/3797069"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":33,"journal-issue":{"issue":"FSE","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3797069"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/3797069","relation":{},"ISSN":["2994-970X"],"issn-type":[{"value":"2994-970X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]}}}