TAMO:Fine-Grained Root Cause Analysis via Tool-Assisted LLM Agent With Multi-Modality Observation Data in Cloud-Native Systems
Open accessThe DOI matches its Crossref record; 54 of the 54 references it cites were found in a registry or an index.
Abstract
Implementing large language models (LLMs)-driven root cause analysis (RCA) in cloud-native systems has become a key topic of modern software operations and maintenance. However, existing LLM-based approaches face three key challenges: multi-modality input constraint, context window limitation, and dynamic dependence graph. To address these issues, we propose a tool-assisted LLM agent with multi-modality observation data for fine-grained RCA, namely TAMO, including multi-modality alignment tool, root cause localization tool, and fault types classification tool. In detail, TAMO unifies multi-modal observation data into time-aligned representations for cross-modal feature consistency. Based on the unified representations, TAMO then invokes its specialized root cause localization tool and fault types classification tool for further identifying root cause and fault type underlying system context. This approach overcomes the limitations of LLMs in processing real-time raw observational data and dynamic service dependencies, guiding the model to generate repair strategies that align with system context through structured prompt design. Experiments on two benchmark datasets demonstrate that TAMO outperforms state-of-the-art (SOTA) approaches with comparable performance.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“the latest research positions them as reverse causal reasoning engines or reasoning hubs, realizing automated Root Cause Analysis (RCA) by scheduling external tools.”
From From Correlation to Intervention: A Survey on Log-Based Causal Analysis for Security and AIOps (2026) · cites this paper as [41]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This division of labor alleviates the computational burden on LLMs, but lacks a feedback verification mechanism for intermediate results between the tools and the LLMs.”
From From Correlation to Intervention: A Survey on Log-Based Causal Analysis for Security and AIOps (2026) · cites this paper as [41]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“TAMO [40] is a tool-assisted LLM-agent framework for fine-grained RCA that integrates multimodal alignment and model tools (e.g., localization/classification tools) to support root-cause analysis in cloud-native systems.”
From TopoEvo: A Topology-Aware Self-Evolving Multi-Agent Framework for Root Cause Analysis in Microservices (2026) · cites this paper as [40]
The cited source says what the claim attributes to it.
In the citing paper
“TAMO[41] proposes an innovative decoupled architecture: first utilizing diffusion models to fuse multimodal observational data, invoking frequency-domain and graph network tools to locate root cause nodes, and finally handing over the structured results to an LLM expert agent for comprehensive decision-making.”
From From Correlation to Intervention: A Survey on Log-Based Causal Analysis for Security and AIOps (2026) · cites this paper as [41]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 3×
“Furthermore, since our research task is relatively novel and includes both fault localization and classification, we incorporate the same fault classifier used in TAMO for methods that do not natively implement fault classification (such as methods [23], [39], [42], etc.) for comparison.”
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“The model is trained with the Adam optimizer [22], and all experiments use a fixed random seed.”
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
DeepLog: Anomaly Detection and Diagnosis from System Logs through Deep Learning
Du, M., Li, F., Zheng, G., & Srikumar, V. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134015 · Cited by 1,835 · cited 1×
“DeepLog[11] modelslogfeaturesvialongshort-termmemorynetworks.”
Graph Neural Network-Based Anomaly Detection in Multivariate Time Series
Deng, A., & Hooi, B. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i5.16523 · Cited by 1,413 · cited 1×
“GDN[10]andGTA[8]constructgraphneuralnetworksusing metricsdatatocapturefaultpropagationpaths.”
Drain: an online log parsing approach with fixed depth tree
He, P., Zhu, J., Zheng, Z., & Lyu, M. R. (2017) · 2017 IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws.2017.13 · Cited by 943 · cited 1×
“…are difficult to extract high-quality features, inspired by previous work [14], [23], we extract event patterns E and keywords W from the raw logs using Drain [16], and by calculating the TF-IDF scores, we select the highest scoring pattern-keyword pairs as the conditional variable c log .”
How Attentive are Graph Attention Networks?
Brody, S., Alon, U., & Yahav, E. (2021) · arXiv · doi:10.48550/arxiv.2105.14491 · Cited by 789
Burns, B., Grant, B., Oppenheimer, D., Brewer, E., & Wilkes, J. (2016) · Communications of the ACM · doi:10.1145/2890784 · Cited by 690 · cited 1×
“Among these, 9 fault types are related to services and pods in the context of Kubernetes (K8s) containers [4], while node faults include 6 types: sudden memory pressure, disk space exhaustion, disk read/write issues, CPU pressure, and slow CPU growth.”
Large language models for software engineering: survey and open problems
Fan, A., Gokkaya, B., Harman, M., Lyubarskiy, M., Sengupta, S., Yoo, S., & Zhang, J. M. (2023) · 2023 IEEE/ACM International Conference on Software Engineering: Future of Software Engineering (ICSE-FoSE) · doi:10.1109/icse-fose59343.2023.00008 · Cited by 650 · cited 1×
“Recently, large language models (LLMs) have demonstrated revolutionary capabilities in automated RCA, opening new avenues for AIOps [9], [12].”
Learning Graph Structures With Transformer for Multivariate Time-Series Anomaly Detection in IoT
Chen, Z., Chen, D., Zhang, X., Yuan, Z., & Cheng, X. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3100509 · Cited by 595 · cited 1×
“GDN[10]andGTA[8]constructgraphneuralnetworksusing metricsdatatocapturefaultpropagationpaths.”
Self-citationLarge Language Models for Software Engineering: Survey and Open Problems
Fan, A., Gokkaya, B., Harman, M., Lyubarskiy, M., Sengupta, S., Yoo, S., & Zhang, J. M. (2023) · arXiv · doi:10.48550/arxiv.2310.03533 · Cited by 523 · cited 1×
“Recently, large language models (LLMs) have demonstrated revolutionary capabilities in automated RCA, opening new avenues for AIOps [9], [12].”
Borg, Omega, and Kubernetes: Lessons learned from three container-management systems over a decade
Burns, B., Grant, B., Oppenheimer, D., Brewer, E., & Wilkes, J. (2016) · Queue · doi:10.1145/2898442.2898444 · Cited by 443
Can Language Models Solve Graph Problems in Natural Language?
Wang, H., Feng, S., He, T., Tan, Z., Han, X., & Tsvetkov, Y. (2023) · neural information processing systems · doi:10.52202/075280-1345 · Cited by 441
The pains and gains of microservices: A Systematic grey literature review
Soldani, J., Tamburri, D. A., & Van Den Heuvel, W.-J. (2018) · Journal of Systems and Software · doi:10.1016/j.jss.2018.09.082 · Cited by 435 · cited 1×
“However, existing LLM-based approaches face three key challenges: multi-modality input constraint, context window limitation, and dynamic dependence graph.”
TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis
Wu, H., Hu, T., Liu, Y., Zhou, H., Wang, J., & Long, M. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2210.02186 · Cited by 431 · cited 2×
“Furthermore, since our research task is relatively novel and includes both fault localization and classification, we incorporate the same fault classifier used in TAMO for methods that do not natively implement fault classification (such as methods [23], [39], [42], etc.) for comparison.”
Zhou, X., Peng, X., Xie, T., Sun, J., Ji, C., Li, W., & Ding, D. (2021) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2018.2887384 · Cited by 410 · cited 1×
“Based on the unified representations, TAMO then invokes its specialized root cause localization tool and fault types classification tool for further identifying root cause and fault type underlying system context.”
Characterizing Microservice Dependency and Performance: Alibaba Trace Analysis
Luo, S., Xu, H., Lu, C., Ye, K., Xu, G., Zhang, L., Ding, Y., He, J., & Xu, C. (2021) · Proceedings of the ACM Symposium on Cloud Computing · doi:10.1145/3472883.3487003 · Cited by 293 · cited 1×
“I N RECENT years, microservice architecture in cloud-native systems has become foundational elements in modern enterprise software development, driving the rapid improvement of distributed systems [25], [30], [37], [45].”
Exploring LLM-Based Agents for Root Cause Analysis
Roy, D., Zhang, X., Bhave, R., Bansal, C., Las-Casas, P., Fonseca, R., & Rajmohan, S. (2024) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/3663529.3663841 · Cited by 268 · cited 2×
“RCAcopilot [6] maps multimodal observation data to predefined events and predicts root cause categories in production through an LLM-driven workflow, and agent-based approaches [35] utilize tool-assisted LLMs to actively retrieve diagnostic data like logs and metrics for localization.”
Self-citationMicroHECL: High-Efficient Root Cause Localization in Large-Scale Microservice Systems
Liu, D., He, C., Peng, X., Lin, F., Zhang, C., Gong, S., Li, Z., Ou, J., & Wu, Z. (2021) · 2021 IEEE/ACM 43rd International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) · doi:10.1109/icse-seip52600.2021.00043 · Cited by 192 · cited 1×
“On one hand, traditional RCA methods [29], [31] typically rely on rule-based anomaly detection or statistical correlation analysis (e.g., causal graphs) [24] to localize faults.”
Automatic Root Cause Analysis via Large Language Models for Cloud Incidents
Chen, Y., Xie, H., Ma, M., Kang, Y., Gao, X., Shi, L., Cao, Y., Gao, X., Fan, H., Wen, M., et al. (2024) · Proceedings of the Nineteenth European Conference on Computer Systems · doi:10.1145/3627703.3629553 · Cited by 190 · cited 3×
“RCAcopilot [6] maps multimodal observation data to predefined events and predicts root cause categories in production through an LLM-driven workflow, and agent-based approaches [35] utilize tool-assisted LLMs to actively retrieve diagnostic data like logs and metrics for localization.”
Self-citationSage: practical and scalable ML-driven performance debugging in microservices
Gan, Y., Liang, M., Dev, S., Lo, D., & Delimitrou, C. (2021) · Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems · doi:10.1145/3445814.3446700 · Cited by 174
Eadro: An End-to-End Troubleshooting Framework for Microservices on Multi-source Data
Lee, C., Yang, T., Chen, Z., Su, Y., & Lyu, M. R. (2023) · 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE) · doi:10.1109/icse48619.2023.00150 · Cited by 149 · cited 7×
“…variable c log , since unstructured log representations are difficult to extract high-quality features, inspired by previous work [14], [23], we extract event patterns E and keywords W from the raw logs using Drain [16], and by calculating the TF-IDF scores, we select the highest…”
InfluentialCollaborative Diffusion for Multi-Modal Face Generation and Editing
Huang, Z., Chan, K. C. K., Jiang, Y., & Liu, Z. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00589 · Cited by 147 · cited 1×
“Diffusion models are a class of generative models based on Markov processes that have demonstrated exceptional performance in the generation of data in various domains, including images [19], voice [34], and time series [47].”
Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling SchemePreprint
Popov, V., Vovk, I., Gogoryan, V., Sadekova, T., Kudinov, M., & Wei, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.13821 · Cited by 144 · cited 1×
“Diffusion models are a class of generative models based on Markov processes that have demonstrated exceptional performance in the generation of data in various domains, including images [19], voice [34], and time series [47].”
Yu, G., Chen, P., Li, Y., Chen, H., Li, X., & Zheng, Z. (2023) · Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering · doi:10.1145/3611643.3616249 · Cited by 140 · cited 1×
“In contrast to directly using raw data for root cause localization, Nezha [46] and DiagFusion [48] convert heterogeneous multimodal data into homogeneous event representations, performing joint analysis through event graphs to achieve root cause localization.”
MULAN: Multi-modal Causal Structure Learning and Root Cause Analysis for Microservice Systems
Zheng, L., Chen, Z., He, J., & Chen, H. (2024) · International World Wide Web Conference (WWW) · doi:10.1145/3589334.3645442 · Cited by 127 · cited 3×
“Therefore, how to perform accurate and efficient root cause analysis in cloud-native systems has become an important research topic recently [14], [51].”
Robust Failure Diagnosis of Microservice System Through Multimodal Data
Zhang, S., Jin, P., Lin, Z., Sun, Y., Zhang, B., Xia, S., Li, Z., Zhong, Z., Ma, M., Jin, W., et al. (2023) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2023.3290018 · Cited by 118 · cited 3×
“Root cause analysis (RCA) aims to quickly correlate features of multiple related entities, localize root cause, identify corresponding fault type, and provide reasonable solutions, thus realizing an automatic fault response mechanism and minimizing human intervention [5], [48].”
An approach to software reliability prediction based on time series modeling
Amin, A. A., Grunske, L., & Colman, A. (2013) · Journal of Systems and Software · doi:10.1016/j.jss.2013.03.045 · Cited by 114 · cited 1×
“This approach overcomes the limitations of LLMs in processing real-time raw observational data and dynamic service dependencies, guiding the model to generate repair strategies that align with system context through structured prompt design.”
RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models
Wang, Z., Liu, Z., Zhang, Y., Zhong, A., Wang, J., Yin, F., Fan, L., Wu, L., & Wen, Q. (2024) · Proceedings of the 33rd ACM International Conference on Information and Knowledge Management · doi:10.1145/3627673.3680016 · Cited by 99 · cited 2×
“Index Terms —Root cause analysis, tool-assisted LLM agent, cloud-native systems, multimodal data, diffusion.”
Key Characteristics of a Container Orchestration Platform to Enable a Modern Application
Khan, A. (2017) · IEEE Cloud Computing · doi:10.1109/mcc.2017.4250933 · Cited by 90 · cited 1×
“Microservices de-compose traditional monolithic applications into independent distributed services, while cloud native technologies leverage containerization and container orchestration to enhance the capabilities for flexible resource allocation and autoscaling [21], [33].”
Outage Prediction and Diagnosis for Cloud Service Systems
Chen, Y., Yang, X., Lin, Q., Zhang, H., Gao, F., Xu, Z., Dang, Y., Zhang, D., Dong, H., Xu, Y., et al. (2019) · The World Wide Web Conference · doi:10.1145/3308558.3313501 · Cited by 85 · cited 1×
“In detail, cloud-native systems are composed of numerous independent microservices and containerized entities (e.g., pod, node) [52], which inevitably brings inter-service dependencies and complex communication patterns.”
Actionable and interpretable fault localization for recurring failures in online service systems
Li, Z., Zhao, N., Li, M., Lu, X., Wang, L., Chang, D., Nie, X., Cao, L., Zhang, W., Sui, K., et al. (2022) · Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering · doi:10.1145/3540250.3549092 · Cited by 70 · cited 1×
“Specifically, we select two state-of-the-art integrated multimodal root cause analysis methods, Eadro [23] and HolisticRCA [14], as well as four unimodal time series analysis methods (i.e., TimesNet [42], SegRNN [28], DejaVu [27], Transformer [39]).”
Self-citationMarwede, N., Röhr, M., van Hoorn, A., & Hasselbring, W. (2009) · Euromicro Conference on Software Maintenance and Reengineering (CSMR) · doi:10.1109/csmr.2009.15 · Cited by 64 · cited 1×
“On one hand, traditional RCA methods [29], [31] typically rely on rule-based anomaly detection or statistical correlation analysis (e.g., causal graphs) [24] to localize faults.”
Diagnosing Performance Issues in Microservices with Heterogeneous Data Source
Hou, C., Jia, T., Wu, Y., Li, Y., & Han, J. (2021) · 2021 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom) · doi:10.1109/ispa-bdcloud-socialcom-sustaincom52081.2021.00074 · Cited by 54 · cited 2×
“Index Terms —Root cause analysis, tool-assisted LLM agent, cloud-native systems, multimodal data, diffusion.”
Han, Y., Du, Q., Huang, Y., Wu, J., Tian, F., & He, C. (2024) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3691620.3695475 · Cited by 53 · cited 1×
“Based on previous research works [14], [15], [23], [48], we select different evaluation metrics to evaluate the performance of model for these two tasks.”
COCA: Generative Root Cause Analysis for Distributed Systems with Code Knowledge
Li, Y., Wu, Y., Liu, J., Jiang, Z., Chen, Z., Yu, G., & Lyu, M. R.-T. (2025) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse55347.2025.00234 · Cited by 49 · cited 1×
“Index Terms —Root cause analysis, tool-assisted LLM agent, cloud-native systems, multimodal data, diffusion.”
RealTCD: Temporal Causal Discovery from Interventional Data with Large Language Model
Li, P., Wang, X. Y., Zhang, Z., Meng, Y., Shen, F., Li, Y., Wang, J., Li, Y., & Zhu, W. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3680042 · Cited by 48 · cited 1×
“On one hand, traditional RCA methods [29], [31] typically rely on rule-based anomaly detection or statistical correlation analysis (e.g., causal graphs) [24] to localize faults.”
Zhang, W., Guo, H., Yang, J., Tian, Z., Zhang, Y., Chaoran, Y., Li, Z., Li, T., Shi, X., Zheng, L., et al. (2024) · Findings of the Association for Computational Linguistics: EMNLP 2024 · doi:10.18653/v1/2024.findings-emnlp.232 · Cited by 35
Informer: Irregular traffic detection for containerized microservices RPC in the real world
Chen, J., Huang, H., & Chen, H. (2022) · High-Confidence Computing · doi:10.1016/j.hcc.2022.100050 · Cited by 24
AI for IT Operations (AIOps) on Cloud Platforms: Reviews, Opportunities and Challenges
Cheng, Q., Sahoo, D., Saha, A., Yang, W., Liu, C., Woo, G., Singh, M., Saverese, S., & Hoi, S. C. H. (2023) · arXiv · doi:10.48550/arxiv.2304.04661 · Cited by 23 · cited 1×
“Index Terms —Root cause analysis, tool-assisted LLM agent, cloud-native systems, multimodal data, diffusion.”
Zhang, W., Guo, H., Yang, J. X., Tian, Z., Zhang, Y., Yan, C., Li, Z., Li, T., Shi, X., Zheng, L., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2404.12135 · Cited by 22 · cited 1×
“Recent works such as RCA-gent [41] and mABC [49] develop LLM-driven automated RCA frameworks that enable accurate fault localization and provide reasonable repair suggestions, thus further advancing the field 1939-1374 © 2025 IEEE.”
Yao, Z., Pei, C., Chen, W., Wang, H., Su, L., Jiang, H., Xie, Z., Nie, X., & Pei, D. (2024) · Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering · doi:10.1145/3663529.3663827 · Cited by 21 · cited 1×
“CoE [44] further supports the operational experience of site reliability engineers as input on the event graph, enhancing the understanding and interpretability of the event.”
Trustworthy decentralized collaborative learning for edge intelligence: A survey
Yu, D., Xie, Z., Yuan, Y., Chen, S., Qiao, J., Wang, Y., Yu, Y. H., Zou, Y., & Zhang, X. L. (2023) · High-Confidence Computing · doi:10.1016/j.hcc.2023.100150 · Cited by 20 · cited 1×
“I N RECENT years, microservice architecture in cloud-native systems has become foundational elements in modern enterprise software development, driving the rapid improvement of distributed systems [25], [30], [37], [45].”
Self-citationZhang, X., Xu, S., Chen, H., Chen, Z., Zhuang, F., Xiong, H., & Yu, D. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3466291 · Cited by 16 · cited 1×
“On the other hand, deep learning (DL) based RCA methods attempt to incorporate multimodal feature fusion and dependency-sensitive graph neural networks (GNNs) [23], [50] to achieve accurate fault localization.”
Self-citationHolistic Root Cause Analysis for Failures in Cloud-Native Systems Through Observability Data
Han, Y., Du, Q., Huang, Y., Li, P., Shi, X., Wu, J., Fang, P., Tian, F., & He, C. (2024) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2024.3478759 · Cited by 16 · cited 5×
“Therefore, how to perform accurate and efficient root cause analysis in cloud-native systems has become an important research topic recently [14], [51].”
InfluentialNoor, J., Faysal, M. B., Amin, M. S., Tabassum, B., Khan, T. R., & Rahman, T. (2024) · High-Confidence Computing · doi:10.1016/j.hcc.2024.100276 · Cited by 16 · cited 1×
“Microservices de-compose traditional monolithic applications into independent distributed services, while cloud native technologies leverage containerization and container orchestration to enhance the capabilities for flexible resource allocation and autoscaling [21], [33].”
An Microservices-Based Openstack Monitoring Tool
Yang, M., & Huang, M. (2019) · IEEE International Conference on Software Engineering and Service Science (ICSESS) · doi:10.1109/icsess47205.2019.9040740 · Cited by 13 · cited 1×
“Traditional RCA methods : Traditional RCA methods are mainly based on statistical correlation analysis techniques, such as anomaly detection based on predefined rules and root cause localization strategies based on causal discovery [7], [43].”
Practical and Scalable ML-Driven Cloud Performance Debugging With Sage
Gan, Y., Liang, M., Dev, S., Lo, D., & Delimitrou, C. (2022) · IEEE Micro · doi:10.1109/mm.2022.3169445 · Cited by 6
Li, Y., Zhang, X., Li, M., Xu, G., Chen, F., Yuan, Y., Zou, Y., Zhao, M., Lu, J., & Yu, D. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3612427 · Cited by 3 · cited 1×
“I N RECENT years, microservice architecture in cloud-native systems has become foundational elements in modern enterprise software development, driving the rapid improvement of distributed systems [25], [30], [37], [45].”
Self-citationSong, L., Han, Y., Guo, Y., & Cai, C. (2024) · High-Confidence Computing · doi:10.1016/j.hcc.2024.100268 · Cited by 2 · cited 1×
“This approach overcomes the limitations of LLMs in processing real-time raw observational data and dynamic service dependencies, guiding the model to generate repair strategies that align with system context through structured prompt design.”
OpenAI, Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.08774 · cited 1×
“Specifically, we use the GPT-4 [1] as the expert model, which gathers the outputs from the previous tools as background knowledge, including: (cid:2) Root Cause Localization Results (from T 2 ): Identifying the root cause location of the fault and the associated system components.”
Li, Y., Zhang, X., Li, M., Xu, G., Chen, F., Yuan, Y., Zou, Y., Zhao, M., Lu, J., & Yu, D. (2024) · arXiv · doi:10.48550/arxiv.2410.08457 · cited 1×
“I N RECENT years, microservice architecture in cloud-native systems has become foundational elements in modern enterprise software development, driving the rapid improvement of distributed systems [25], [30], [37], [45].”
Self-citationCOCA: Generative Root Cause Analysis for Distributed Systems with Code Knowledge
Li, Y., Wu, Y., Liu, J., Jiang, Z., Chen, Z., Yu, G., & Lyu, M. R. (2025) · arXiv · doi:10.48550/arxiv.2503.23051 · cited 1×
“Index Terms —Root cause analysis, tool-assisted LLM agent, cloud-native systems, multimodal data, diffusion.”
SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting
Lin, S., Lin, W., Wu, W., Zhao, F., Mo, R., & Zhang, H. (2023) · arXiv · doi:10.48550/arxiv.2308.11200 · cited 1×
“Specifically, we select two state-of-the-art integrated multimodal root cause analysis methods, Eadro [23] and HolisticRCA [14], as well as four unimodal time series analysis methods (i.e., TimesNet [42], SegRNN [28], DejaVu [27], Transformer [39]).”
Research works printed but not linked: 3
- Ho, Denoising diffusion probabilistic models, 6840
- Ke, LightGBM: A highly efficient gradient boosting decision tree, 3149
- Sarda, ADARMA auto-detection and auto-remediation of microservice anomalies by leveraging large language models, 200
Cited by
ThinkFL: Self-Refining Failure Localization for Microservice Systems via Reinforcement Fine-Tuning
Zhang, L., Zhai, Y., Jia, T., Duan, C., Yu, S., Gao, J., Ding, B., Wu, Z., & Li, Y. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3789262 · Cited by 31
Agentic Memory Enhanced Recursive Reasoning for Root Cause Localization in Microservices
Zhang, L.-Z., Jia, T., Zhai, Y.-P., Pan, L.-Y., Duan, C.-M., He, M.-H., Jia, M., & Li, Y. (2026) · SEIP@ICSE · doi:10.1145/3786583.3786853 · Cited by 16
Hypothesize-Then-Verify: Speculative Root Cause Analysis for Microservices with Pathwise Parallelism
Zhang, L., Jia, T., Zhai, Y., Pan, L., Duan, C., He, M., Xiao, P., & Li, Y. (2026) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3786582.3786803 · Cited by 17
“…and reasoning capabilities, LLMs can reduce dependence on handcrafted features while offering strong cross-platform adaptability, task generalization, and flexibility, thereby alleviating the limitations of conventional methods [2, 4, 8–10, 12, 13, 17, 18, 21, 24, 28, 31, 34, 35, 38, 39].”
Riddell, E., Riddell, J., Sun, G., Antkiewicz, M., & Czarnecki, K. (2026) · IEEE/ACM International Conference on AI Foundation Models and Software Engineering (FORGE) · doi:10.1145/3793655.3793732 · Cited by 15
“More recent work integrates LLMs as agents into retrieval-or tool-augmented frameworks [25, 28, 50] or multi-agent systems [14, 21, 35, 40, 48].”
Tang, Y., Chen, K., Yue, L., Fan, J., Zhou, C., Li, X., Zhang, Y., Zhao, M., Kai, S., Guo, K., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.17491 · Cited by 10
“Frameworks like RCAgent [262] and TAMO [263] leverage tool-enhanced LLMs to perform root cause analysis for industrial systems or microservices architectures.”
Metadata
- Authors
- Zhang, X., Wang, Q., Li, M., Yuan, Y., Xiao, M., Zhuang, F., & Yu, D.
- Affiliations
- Shandong University (CN)
- Beihang University (CN)
- Venue
- IEEE Transactions on Services Computing
- Published
- 2025-11
- Volume
- 18
- Issue
- 6
- Pages
- 4221-4233
- ISSN
- 1939-1374 (ISSN-L)
- 2372-0204
- OpenAlex
- W4415933773
- Cited by
- 15
- References
- 38
- Citations by year
- 2026: 15
- FWCI
- 6.22
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Services Computing (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (62202273, 62176014)
- Joint Key Funds of National Natural Science Foundation of China (U24B20149)
- Major Basic Research Program of Shandong Provincial Natural Science Foundation (ZR2025ZD18)
- China Postdoctoral Science Foundation (2024M761806)
- Fundamental Research Funds for the Central Universities
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Software System Performance and Reliability
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Information Systems › Cloud Computing and Resource Management
- Keywords
- root cause analysis, large language models, LLM agents, cloud-native systems, root cause localization, fault classification, cross-modal alignment, service dependency graph, repair strategies, prompt engineering
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.