CoChat
Sign Up
Cited by 51Software System Performance and ReliabilitySoftware Engineering ResearchCloud Computing and Resource Management

A Survey of AIOps in the Era of Large Language Models

Open access
Zhang, Lingzhe, Jia, Tong, Jia, Mengxi, Wu, Yifan, Liu, Aiwei, Yang, Yong, Wu, Zhonghai, Hu, Xuming +2 more·2026·ACM Computing Surveys
DOI 10.1145/3746635
Open this paper in CoChat — free accountOpen PDF

Abstract

As large language models (LLMs) grow increasingly sophisticated and pervasive, their application to various Artificial Intelligence for IT Operations (AIOps) tasks has garnered significant attention. However, a comprehensive understanding of the impact, potential, and limitations of LLMs in AIOps remains in its infancy. To address this gap, we conducted a detailed survey of LLM4AIOps, focusing on how LLMs can optimize processes and improve outcomes in this domain. We analyzed 183 research articles published between January 2020 and December 2024 to answer four key research questions (RQs). In RQ1, we examine the diverse failure data sources utilized, including advanced LLM-based processing techniques for legacy data and the incorporation of new data sources enabled by LLMs. RQ2 explores the evolution of AIOps tasks, highlighting the emergence of novel tasks and the publication trends across these tasks. RQ3 investigates the various LLM-based methods applied to address AIOps challenges. Finally, RQ4 reviews evaluation methodologies tailored to assess LLM-integrated AIOps approaches. Based on our findings, we discuss the state-of-the-art advancements and trends, identify gaps in existing research, and propose promising directions for future exploration.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3746635

Cites

59 of 59 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

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?

  • Early research on Internet operations demonstrated that even minor configuration errors or policy mistakes can result in unexpected and widespread failures.

    “Early research on Internet operations demonstrated that even minor configuration errors or policy mistakes can result in unexpected and widespread failures [45].”

    From Large language models for agentic NetOps and AIOps: Architectures, evaluation, and safety (2027) · cites this paper as [45]

    The Introduction (page unavailable) says even minor software glitches can cause service interruptions and substantial losses in large-scale systems. The failure-category discussion also names software configuration errors, but our copy does not establish that early Internet-operations research found minor configuration or policy mistakes causing unexpected, widespread failures. (LLM, conf=0.78)

    Experimental — accuracy not yet measured

  • The assumption about structured reasoning is crucial for improving practical efficiency.

    “This assumption about structured reasoning is crucial for improving practical efficiency [48], [49], [50].”

    From Large language models for agentic NetOps and AIOps: Architectures, evaluation, and safety (2027) · cites this paper as [49]

    The “Chain of Thoughts (CoT)” section (page unavailable) says that structuring prompts into intermediate reasoning steps enhances LLMs’ performance on multistep AIOps tasks. It does not say that an assumption about structured reasoning is crucial to practical efficiency; Section 7.1 discusses efficiency in terms of computational cost and performance instead. (LLM, conf=0.78)

    Experimental — accuracy not yet measured

  • A complementary research approach employs causal inference, dependency models, and event-related structures to explain the causes of observed symptoms.

    “A complementary research approach employs causal inference, dependency models, and event-related structures to explain the causes of observed symptoms [48], [49], [50].”

    From Large language models for agentic NetOps and AIOps: Architectures, evaluation, and safety (2027) · cites this paper as [49]

    Section 4.2, “Root Cause Analysis” (page not provided), says failure localization often uses causal discovery and examines relationships among input data to identify where an anomaly occurred. The copy does not establish that dependency models or event-related structures are used to explain the causes of observed symptoms; its discussion of event templates in Section 3.1 concerns log preprocessing. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

  • A hybrid design where causal inference constructs or updates a fault graph and the LLM turns operator intent into queries, requests additional evidence, explains the causal path, and prepares a reviewable mitigation proposal improves explainability and can reduce repeated reasoning over raw telemetry and runbook context.

    “This hybrid design has two advantages.First, it improves explainability, because the diagnosis is grounded in a causal path rather than a free-form narrative.Second, it can reduce repeated reasoning over raw telemetry and runbook context, because the causal graph narrows the candidate space before the LLM is asked to summarise, compare, or prepare an action proposal [49], [50].”

    From Large language models for agentic NetOps and AIOps: Architectures, evaluation, and safety (2027) · cites this paper as [49]

    Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.

    Experimental — accuracy not yet measured

  • Work on mining causes of network events from log data uses causal inference to go beyond co-occurrence and recover likely causal relationships among network events.

    “Work on mining causes of network events from log data uses causal inference to go beyond co-occurrence and recover likely causal relationships among network events [49].”

    From Large language models for agentic NetOps and AIOps: Architectures, evaluation, and safety (2027) · cites this paper as [49]

    Section 4.2, Root Cause Analysis, says failure localization often uses causal discovery and may identify a log entry marking the onset of an anomaly. The Chain of Thoughts section also reports work identifying causative relationships between events. Neither passage specifies network events or says the method goes beyond co-occurrence; no page numbers are available in our copy. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

1 of the 60 references couldn’t be matched to a known paper.

Research works printed but not linked: 123

  1. 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 Proceedings of the 2023 IEEE/ACM 45th International Conference on Software Engineering. IEEE, 1737-1749.
  2. Khalid Ayed Alharthi, Arshad Jhumka, Sheng Di, Lin Gui, Franck Cappello, and Simon McIntosh-Smith. 2023. Time machine: Generative real-time model for failure (and lead time) prediction in hpc systems. In Proceedings of the 2023 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks. IEEE, 508-521.
  3. Bhavya Bhavya, Paulina Toro Isaza, Yu Deng, Michael Nidd, Amar Prakash Azad, Larisa Shwartz, and ChengXiang Zhai. 2023. Exploring large language models for low-resource IT information extraction. In Proceedings of the 2023 IEEE International Conference on Data Mining Workshops. IEEE, 1203-1212.
  4. Defu Cao, Furong Jia, Sercan O Arik, Tomas Pfister, Yixiang Zheng, Wen Ye, and Yan Liu. 2024. TEMPO: Prompt-based generative pre-trained transformer for time series forecasting. In Proceedings of the 12th International Conference on Learning Representations.
  5. Ching Chang, Wei-Yao Wang, Wen-Chih Peng, and Tien-Fu Chen. 2025. Llm4ts: Aligning pre-trained LLMs as data- efficient time-series forecasters. ACM Transactions on Intelligent Systems and Technology 16, 3 (2025), 1-20.
  6. Georgios Chatzigeorgakidis, Konstantinos Lentzos, and Dimitrios Skoutas. 2024. MultiCast: Zero-shot multivariate time series forecasting using LLMs. In Proceedings of the 2024 IEEE 40th International Conference on Data Engineering Workshops. IEEE, 119-127.
  7. Y. Chen, M. Shetty, G. Somashekar, et al. 2025. AIOpsLab: A holistic framework to evaluate AI agents for enabling autonomous clouds. arXiv preprint arXiv:2501.06706. · arXiv
  8. Yakun Chen, Xianzhi Wang, and Guandong Xu. 2023. Gatgpt: A pre-trained large language model with graph atten- tion network for spatiotemporal imputation. arXiv:2311.14332. Retrieved from https://arxiv.org/abs/2311.14332 · arXiv
  9. Qian Cheng, Doyen Sahoo, Amrita Saha, Wen zhuo Yang, Chen ghao Liu, Gerald Woo, Manpreet Singh, Silvio Saverese, and Steven C. H. Hoi. 2023. AI for it operations (aiops) on cloud platforms: Reviews, opportunities and challenges. arXiv preprint arXiv:2304.04661. · arXiv
  10. Tianyu Cui, Shiyu Ma, Ziang Chen, Tong Xiao, Shimin Tao, Yilun Liu, Shenglin Zhang, Duoming Lin, Changchang Liu, and Yuzhe Cai. 2024. Logeval: A comprehensive benchmark suite for large language models in log analysis. arXiv preprint arXiv:2407.01896. · arXiv
  11. Abhimanyu Das, Weihao Kong, Rajat Sen, and Yichen Zhou. 2024. A decoder-only foundation model for time-series forecasting. In Proceedings of the 41st International Conference on Machine Learning.
  12. Jiaxiang Dong, Haixu Wu, Haoran Zhang, Li Zhang, Jianmin Wang, and Mingsheng Long. 2023. Simmtm: A simple pre-training framework for masked time-series modeling. Advances in Neural Information Processing Systems 36 (2023), 29996-30025.
  13. Vijay Ekambaram, Arindam Jati, Nam H. Nguyen, Pankaj Dayama, Chandra Reddy, Wesley M. Gifford, and Jayant Kalagnanam. 2024. Ttms: Fast multi-level tiny time mixers for improved zero-shot and few-shot forecasting of mul- tivariate time series. 8, 22 (2024). arXiv preprint arXiv:2401.03955. · arXiv
  14. Asma Fariha, Vida Gharavian, Masoud Makrehchi, Shahryar Rahnamayan, Sanaa Alwidian, and Akramul Azim. 2024. Log anomaly detection by leveraging LLM-based parsing and embedding with attention mechanism. In Proceedings of the 2024 IEEE Canadian Conference on Electrical and Computer Engineering. IEEE, 859-863.
  15. A. Garza, C. Challu, and M. Mergenthaler-Canseco. 2023. TimeGPT-1. arXiv preprint arXiv:2310.03589. · arXiv
  16. Nate Gruver, Marc Finzi, Shikai Qiu, and Andrew G. Wilson. 2023. Large language models are zero-shot time series forecasters. Advances in Neural Information Processing Systems 36 (2023), 19622-19635.
  17. Jindong Gu, Zhen Han, Shuo Chen, Ahmad Beirami, Bailan He, Gengyuan Zhang, Ruotong Liao, Yao Qin, Volker Tresp, and Philip Torr. 2023. A systematic survey of prompt engineering on vision-language foundation models. arXiv:2307.12980. Retrieved from https://arxiv.org/abs/2307.12980 · arXiv
  18. Hongcheng Guo, Jian Yang, Jiaheng Liu, Liqun Yang, Linzheng Chai, Jiaqi Bai, Junran Peng, Xiaorong Hu, Chao Chen, Dongfeng Zhang, et al. 2024. OWL: A large language model for IT operations. In Proceedings of the 12th International Conference on Learning Representations.
  19. Hongcheng Guo, Wei Zhang, Anjie Le, Jian Yang, Jiaheng Liu, Zhoujun Li, Tieqiao Zheng, Shi Xu, Runqiang Zang, and Liangfan Zheng. 2024. Lemur: Log parsing with entropy sampling and chain-of-thought merging. arXiv preprint arXiv:2402.18205. · arXiv
  20. Pranjal Gupta, Harshit Kumar, Debanjana Kar, Karan Bhukar, Pooja Aggarwal, and Prateeti Mohapatra. 2023. Learn- ing representations on logs for AIOps. In Proceedings of the 2023 IEEE 16th International Conference on Cloud Com- puting. IEEE, 155-166.
  21. Fatemeh Hadadi, Qinghua Xu, Domenico Bianculli, and Lionel Briand. 2024. Anomaly detection on unstable logs with gpt models. arXiv preprint arXiv:2406.07467. · arXiv
  22. Yongqi Han, Qingfeng Du, Ying Huang, Jiaqi Wu, Fulong Tian, and Cheng He. 2024. The potential of one-shot failure root cause analysis: Collaboration of the large language model and small classifier. In Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering. 931-943.
  23. Ahatsham Hayat and Mohammad R. Hasan. 2025. A context-aware approach for enhancing data imputation with pre-trained language models. In Proceedings of the 31st International Conference on Computational Linguistics. 5668-5685.
  24. Minghua He, Tong Jia, Chiming Duan, Huaqian Cai, Ying Li, and Gang Huang. 2024. LLMeLog: An approach for anomaly detection based on LLM-enriched log events. In Proceedings of the 2024 IEEE 35th International Symposium on Software Reliability Engineering. IEEE, 132-143.
  25. J. Zhu, S. He, P. He, et al. 2023. Loghub: A large collection of system log datasets for AI-driven log analytics. IEEE 34th International Symposium on Software Reliability Engineering (ISSRE). IEEE.
  26. Stefan Hegselmann, Alejandro Buendia, Hunter Lang, Monica Agrawal, Xiaoyi Jiang, and David Sontag. 2023. Tabllm: Few-shot classification of tabular data with large language models. In Proceedings of the International Conference on Artificial Intelligence and Statistics. PMLR, 5549-5581.
  27. Junjie Huang, Zhihan Jiang, Jinyang Liu, Yintong Huo, Jiazhen Gu, Zhuangbin Chen, Cong Feng, Hui Dong, Zengyin Yang, and Michael R. Lyu. 2024. Demystifying and extracting fault-indicating information from logs for failure diagnosis. In Proceedings of the 2024 IEEE 35th International Symposium on Software Reliability Engineering. IEEE, 511-522.
  28. Shaohan Huang, Yi Liu, Jiaxing Qi, Jing Shang, Zhiwen Xiao, Carol Fung, Zhihui Wu, Hailong Yang, Zhongzhi Luan, and Depei Qian. 2024. Gloss: Guiding large language models to answer questions from system logs. In Proceedings of the 2024 IEEE International Conference on Software Analysis, Evolution and Reengineering. IEEE, 91-101.
  29. Azam Ikram, Sarthak Chakraborty, Subrata Mitra, Shiv Saini, Saurabh Bagchi, and Murat Kocaoglu. 2022. Root cause analysis of failures in microservices through causal discovery. Advances in Neural Information Processing Systems 35 (2022), 31158-31170.
  30. Yuhe JI, Jing HAN, Yongxin ZHAO, Shenglin ZHANG, and Zican GONG. 2023. Log anomaly detection through GPT-2 for large scale systems. ZTE Communications 21, 3 (2023), 70.
  31. Tong Jia, Yifan Wu, Chuanjia Hou, and Ying Li. 2021. Logflash: Real-time streaming anomaly detection and diagnosis from system logs for large-scale software systems. In Proceedings of the 2021 IEEE 32nd International Symposium on Software Reliability Engineering. IEEE, 80-90.
  32. Zhihan Jiang, Jinyang Liu, Zhuangbin Chen, Yichen Li, Junjie Huang, Yintong Huo, Pinjia He, Jiazhen Gu, and Michael R Lyu. 2024. Lilac: Log parsing using LLMs with adaptive parsing cache. Proceedings of the ACM on Software Engineering 1, FSE (2024), 137-160.
  33. Hongwei Jin, George Papadimitriou, Krishnan Raghavan, Pawel Zuk, Prasanna Balaprakash, Cong Wang, Anirban Mandal, and Ewa Deelman. 2024. Large language models for anomaly detection in computational workflows: From supervised fine-tuning to in-context learning. In Proceedings of the 2024 SC24: International Conference for High Per- formance Computing, Networking, Storage and Analysis SC. IEEE Computer Society, 1466-1482.
  34. JMing Jin, Shiyu Wang, Lintao Ma, Zhixuan Chu, James Y. Zhang, Xiaoming Shi, Pin-Yu Chen, Yuxuan Liang, Yuan- Fang Li, and Shirui Pan. 2023. Time-LLM: Time series forecasting by reprogramming large language models. The Twelfth International Conference on Learning Representations.
  35. Pengxiang Jin, Shenglin Zhang, Minghua Ma, Haozhe Li, Yu Kang, Liqun Li, Yudong Liu, Bo Qiao, Chaoyun Zhang, Pu Zhao, et al. 2023. Assess and summarize: Improve outage understanding with large language models. In Proceed- ings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 1657-1668.
  36. Yuyuan Kang, Xiangdong Huang, Shaoxu Song, Lingzhe Zhang, Jialin Qiao, Chen Wang, Jianmin Wang, and Julian Feinauer. 2022. Separation or not: On handing out-of-order time-series data in leveled lsm-tree. In Proceedings of the 2022 IEEE 38th International Conference on Data Engineering. IEEE, 3340-3352.
  37. Egil Karlsen, Xiao Luo, Nur Zincir-Heywood, and Malcolm Heywood. 2024. Large language models and unsupervised feature learning: Implications for log analysis. Annals of Telecommunications 79, 11 (2024), 711-729.
  38. Subina Khanal, Seshu Tirupathi, Giulio Zizzo, Ambrish Rawat, and Torben Bach Pedersen. 2024. Domain adaptation for time series transformers using One-step fine-tuning. AAAI Conference on Artificial Intelligence.
  39. Pitikorn Khlaisamniang, Prachaya Khomduean, Kriangkrai Saetan, and Supasin Wonglapsuwan. 2023. Generative AI for self-healing systems. In Proceedings of the 2023 18th International Joint Symposium on Artificial Intelligence and Natural Language Processing. IEEE, 1-6.
  40. Donghyun Kim, Sriram Ravula, Taemin Ha, Alexandros G. Dimakis, Daehyeok Kim, and Aditya Akella. 2024. Large language models as realistic microservice trace generators. arXiv preprint arXiv:2502.17439. · arXiv
  41. Barbara Kitchenham, O. Pearl Brereton, David Budgen, Mark Turner, John Bailey, and Stephen Linkman. 2009. Sys- tematic literature reviews in software engineering-a systematic literature review. Information and Software Technol- ogy 51, 1 (2009), 7-15.
  42. Van-Hoang Le and Hongyu Zhang. 2021. Log-based anomaly detection without log parsing. In Proceedings of the 2021 36th IEEE/ACM International Conference on Automated Software Engineering. IEEE, 492-504.
  43. Van-Hoang Le and Hongyu Zhang. 2023. Log parsing: How far can ChatGPT Go?. In Proceedings of the 2023 38th IEEE/ACM International Conference on Automated Software Engineering. IEEE, 1699-1704.
  44. Guoliang Li, Xuanhe Zhou, Ji Sun, Xiang Yu, Yue Han, Lianyuan Jin, Wenbo Li, Tianqing Wang, and Shifu Li. 2021. Opengauss: An autonomous database system. Proceedings of the VLDB Endowment 14, 12 (2021), 3028-3042.
  45. Peiwen Li, Xin Wang, Zeyang Zhang, Yuan Meng, Fang Shen, Yue Li, Jialong Wang, Yang Li, and Wenweu Zhu. 2024. LLM-enhanced causal discovery in temporal domain from interventional data. arXiv e-prints, 2024: arXiv:2404.14786. · arXiv
  46. Yifei Lin, Hanqiu Deng, and Xingyu Li. 2024. FastLogAD: Log anomaly detection with mask-guided pseudo anomaly generation and discrimination. arXiv preprint arXiv:2404.08750. · arXiv
  47. Haoxin Liu, Zhiyuan Zhao, Jindong Wang, Harshavardhan Kamarthi, and B. Aditya Prakash. 2024. LSTPrompt: Large language models as zero-shot time series forecasters by long-short-term prompting. Findings of the Association for Computational Linguistics ACL 2024. 7832-7840.
  48. Yilun Liu, Yuhe Ji, Shimin Tao, Minggui He, Weibin Meng, Shenglin Zhang, Yongqian Sun, Yuming Xie, Boxing Chen, and Hao Yang. 2024. Loglm: From task-based to instruction-based automated log analysis. arXiv preprint arXiv:2410.09352. · arXiv
  49. Yuhe Liu, Changhua Pei, Longlong Xu, Bohan Chen, Mingze Sun, Zhirui Zhang, Yongqian Sun, Shenglin Zhang, Kun Wang, and Haiming Zhang. 2023. Opseval: A comprehensive task-oriented aiops benchmark for large language models. arXiv preprint arXiv:2310.07637. · arXiv
  50. Yong Liu, Haoran Zhang, Chenyu Li, Xiangdong Huang, Jianmin Wang, and Mingsheng Long. 2024. Timer: Gen- erative pre-trained transformers are large time series models. In Proceedings of the 41st International Conference on Machine Learning.
  51. Yingzhe Lyu, Heng Li, Zhen Ming (Jack) Jiang, and Ahmed E. Hassan. 2023. Assessing the maturity of model main- tenance techniques for AIOps solutions. arXiv preprint arXiv:2311.03213. · arXiv
  52. A. Hamou-Lhadj, M. Mehrabi, and H. Moosavi. 2024. The effectiveness of compact fine-tuned LLMs in log parsing. In Proceedings of the 2024 IEEE International Conference on Software Maintenance and Evolution. IEEE, 97-109.
  53. Lipeng Ma, Weidong Yang, Sihang Jiang, Ben Fei, Mingjie Zhou, Shuhao Li, Bo Xu, and Yanghua Xiao. 2024. Luk: Empowering log understanding with expert knowledge from large language models. arXiv preprint arXiv:2409.01909. · arXiv
  54. Lipeng Ma, Weidong Yang, Bo Xu, Sihang Jiang, Ben Fei, Jiaqing Liang, Mingjie Zhou, and Yanghua Xiao. 2024. Knowlog: Knowledge enhanced pre-trained language model for log understanding. In Proceedings of the 46th IEEE/ACM International Conference on Software Engineering. 1-13.
  55. Zeyang Ma, An Ran Chen, Dong Jae Kim, Tse-Hsun Chen, and Shaowei Wang. 2024. LLMParser: An exploratory study on using large language models for log parsing. In Proceedings of the IEEE/ACM 46th International Conference on Software Engineering. 1-13.
  56. Ehud Malul, Yair Meidan, Dudu Mimran, Yuval Elovici, and Asaf Shabtai. 2024. GenKubeSec: LLM-Based kubernetes misconfiguration detection, localization, reasoning, and remediation. arXiv:2405.19954. Retrieved from https://arxiv. org/abs/2405.19954 · arXiv
  57. Maryam Mehrabi, Abdelwahab Hamou-Lhadj, and Hossein Moosavi. 2024. The effectiveness of compact fine-tuned LLMs in log parsing. In Proceedings of the 2024 IEEE International Conference on Software Maintenance and Evolution. IEEE, 1-12.
  58. Shervin Minaee, Tomas Mikolov, Narjes Nikzad, Meysam Chenaghlu, Richard Socher, Xavier Amatriain, and Jianfeng Gao. 2024. Large language models: A survey. arXiv 2024. arXiv preprint arXiv:2402.06196. · arXiv
  59. Francesco Minna, Fabio Massacci, and Katja Tuma. 2024. Analyzing and mitigating (with LLMs) the security miscon- figurations of helm charts from artifact hub. arXiv preprint arXiv:2403.09537. · arXiv
  60. Panagiotis Misiakos, Chris Wendler, and Markus Püschel. 2023. Learning DAGs from data with few root causes. Advances in Neural Information Processing Systems 36 (2023), 16865-16888.
  61. Priyanka Mudgal, Bijan Arbab, and Swaathi Sampath Kumar. 2024. CrashEventLLM: Predicting system crashes with large language models. In Proceedings of the 2024 International Conference on Information Technology and Computing. IEEE, 72-76.
  62. Priyanka Mudgal and Rita Wouhaybi. 2023. An assessment of ChatGPT on log data. In Proceedings of the International Conference on AI-generated Content. Springer, 148-169.
  63. Zakeya Namrud, Komal Sarda, Marin Litoiu, Larisa Shwartz, and Ian Watts. 2024. KubePlaybook: A repository of ansible playbooks for kubernetes auto-remediation with LLMs. In Companion of the 15th ACM/SPEC International Conference on Performance Engineering. 57-61.
  64. Harold Ott, Jasmin Bogatinovski, Alexander Acker, Sasho Nedelkoski, and Odej Kao. 2021. Robust and transferable anomaly detection in log data using pre-trained language models. In Proceedings of the 2021 IEEE/ACM International Workshop on Cloud Intelligence. IEEE, 19-24.
  65. Jonathan Pan, Wong Swee Liang, and Yuan Yidi. 2024. Raglog: Log anomaly detection using retrieval augmented generation. In Proceedings of the 2024 IEEE World Forum on Public Safety Technology. IEEE, 169-174.
  66. Guansong Pang, Chunhua Shen, Longbing Cao, and Anton Van Den Hengel. 2021. Deep learning for anomaly detec- tion: A review. ACM Computing Surveys 54, 2 (2021), 1-38.
  67. Gijun Park and Dohoon Kim. 2023. Formulating an korean LLM-based interactive assistant for enhanced IT collab- oration in microservice environments. In Proceedings of the 2023 IEEE 8th International Conference on Smart Cloud. IEEE, 176-181.
  68. Robin D. Pesl, Miles Stötzner, Ilche Georgievski, and Marco Aiello. 2023. Uncovering LLMs for service-composition: Challenges and opportunities. In Proceedings of the International Conference on Service-Oriented Computing. Springer, 39-48.
  69. Pankaj Prasad and Charley Rich. 2018. Market guide for aiops platforms. Retrieved March 12, 2020 (2018), 2-9.
  70. Kashif Rasul, Arjun Ashok, Andrew Robert Williams, Arian Khorasani, George Adamopoulos, Rishika Bhagwatkar, Marin Biloš, Hena Ghonia, Nadhir Hassen, Anderson Schneider, et al. 2023. Lag-llama: Towards foundation models for time series forecasting. In Proceedings of the Robustness of Few-shot and Zero-shot Learning in Large Foundation Models.
  71. Youcef Remil, Anes Bendimerad, Romain Mathonat, and Mehdi Kaytoue. 2024. Aiops solutions for incident manage- ment: Technical guidelines and a comprehensive literature review. arXiv preprint arXiv:2404.01363. · arXiv
  72. 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. Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering. 208-219.
  73. Pranab Sahoo, Ayush Kumar Singh, Sriparna Saha, Vinija Jain, Samrat Mondal, and Aman Chadha. 2024. A sys- tematic survey of prompt engineering in large language models: Techniques and applications. arXiv preprint arXiv:2402.07927. · arXiv
  74. Komal Sarda. 2023. Leveraging large language models for auto-remediation in microservices architecture. In Pro- ceedings of the 2023 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion. IEEE, 16-18.
  75. Komal Sarda, Zakeya Namrud, Marin Litoiu, Larisa Shwartz, and Ian Watts. 2024. Leveraging large language models for the auto-remediation of microservice applications: An experimental study. In Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering. 358-369.
  76. Komal Sarda, Zakeya Namrud, Raphael Rouf, Harit Ahuja, Mohammadreza Rasolroveicy, Marin Litoiu, Larisa Shwartz, and Ian Watts. 2023. Adarma auto-detection and auto-remediation of microservice anomalies by leveraging large language models. In Proceedings of the 33rd Annual International Conference on Computer Science and Software Engineering. 200-205.
  77. Jahanggir Hossain Setu, Md Shazzad Hossain, Nabarun Halder, Ashraful Islam, and M. Ashraful Amin. 2024. Opti- mizing software release management with GPT-enabled log anomaly detection. In Proceedings of the International Conference on Pattern Recognition. Springer, 351-365.
  78. Honghao Shi, Longkai Cheng, Wenli Wu, Yuhang Wang, Xuan Liu, Shaokai Nie, Weixv Wang, Xuebin Min, Chunlei Men, and Yonghua Lin. 2024. Enhancing cluster resilience: LLM-agent based autonomous intelligent cluster diagnosis system and evaluation framework. arXiv preprint arXiv:2411.05349. · arXiv
  79. Jie Shi, Sihang Jiang, Bo Xu, Jiaqing Liang, Yanghua Xiao, and Wei Wang. 2023. ShellGPT: Generative pre-trained transformer model for shell language understanding. In Proceedings of the 2023 IEEE 34th International Symposium on Software Reliability Engineering. IEEE, 671-682.
  80. Jing Su, Chufeng Jiang, Xin Jin, Yuxin Qiao, Tingsong Xiao, Hongda Ma, Rong Wei, Zhi Jing, Jiajun Xu, and Jun- hong Lin. 2024. Large language models for forecasting and anomaly detection: A systematic literature review. arXiv preprint arXiv:2402.10350. · arXiv
  81. Yicheng Sui, Yuzhe Zhang, Jianjun Sun, Ting Xu, Shenglin Zhang, Zhengdan Li, Yongqian Sun, Fangrui Guo, Junyu Shen, Yuzhi Zhang, et al. 2023. LogKG: Log failure diagnosis through knowledge graph. IEEE Transactions on Services Computing 16, 5 (2023), 3493-3507.
  82. Chenxi Sun, Hongyan Li, Yaliang Li, and Shenda Hong. 2024. TEST: Text prototype aligned embedding to activate LLM's ability for time series. In Proceedings of the 12th International Conference on Learning Representations.
  83. Yuchen Sun, Yanpiao Chen, Haotian Zhao, and Shan Peng. 2023. Design and development of a log management system based on cloud native architecture. In Proceedings of the 2023 9th International Conference on Systems and Informatics. IEEE, 1-6.
  84. Yicheng SUN, Jacky Keung, Zhen Yang, Shuo Liu, and Hi Kuen Yu. 2024. Semirald: A semi-supervised hybrid language model for robust anomalous log detection. Information and Software Technology 183 (2025), 107743.
  85. Yongqian Sun, Binpeng Shi, Mingyu Mao, Minghua Ma, Sibo Xia, Shenglin Zhang, and Dan Pei. 2024. ART: A unified unsupervised framework for incident management in microservice systems. In Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering. 1183-1194.
  86. Łukasz Tulczyjew, Kinan Jarrah, Charles Abondo, Dina Bennett, and Nathanael Weill. 2024. LLMcap: Large language model for unsupervised PCAP failure detection. In Proceedings of the 2024 IEEE International Conference on Commu- nications Workshops. IEEE, 1559-1565.
  87. Lu Wang, Chaoyun Zhang, Ruomeng Ding, Yong Xu, Qihang Chen, Wentao Zou, Qingjun Chen, Meng Zhang, Xue- dong Gao, Hao Fan, et al. 2023. Root cause analysis for microservice systems via hierarchical reinforcement learning from human feedback. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 5116-5125.
  88. Qing Wang, Wubai Zhou, Chunqiu Zeng, Tao Li, Larisa Shwartz, and Genady Ya Grabarnik. 2017. Constructing the knowledge base for cognitive it service management. In Proceedings of the 2017 IEEE International Conference on Services Computing. IEEE, 410-417.
  89. Sheng-Kai Wang, Shang-Pin Ma, Chen-Hao Chao, and Guan-Hong Lai. 2023. Low-code ChatOps for microservices systems using service composition. In Proceedings of the 2023 IEEE International Conference on e-Business Engineering. IEEE, 55-62.
  90. Xinjie Wei, Jie Wang, Chang-ai Sun, Dave Towey, Shoufeng Zhang, Wanqing Zuo, Yiming Yu, Ruoyi Ruan, and Guyang Song. 2024. Log-based anomaly detection for distributed systems: State of the art, industry experience, and open issues. Journal of Software: Evolution and Process 36, 8 (2024), e2650.
  91. Jinfeng Wen, Zhenpeng Chen, Federica Sarro, Zixi Zhu, Yi Liu, Haodi Ping, and Shangguang Wang. 2025. LLM- based misconfiguration detection for AWS serverless computing. ACM Transactions on Software Engineering and Methodology.
  92. Yi Xiao, Van-Hoang Le, and Hongyu Zhang. 2024. Free: Towards more practical log parsing with large language models. In Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering. 153-165.
  93. Yi Xiao, Van-Hoang Le, and Hongyu Zhang. 2024. Stronger, faster, and cheaper log parsing with LLMs. arXiv e-prints. arXiv:2406.06156. · arXiv
  94. Zhiqiang Xie, Yujia Zheng, Lizi Ottens, Kun Zhang, Christos Kozyrakis, and Jonathan Mace. 2024. Cloud atlas: effi- cient fault localization for cloud systems using language models and causal insight. arXiv preprint arXiv:2407.08694. · arXiv
  95. Miao Xiong, Zhiyuan Hu, Xinyang Lu, Yifei Li, Jie Fu, Junxian He, and Bryan Hooi. 2023. Can LLMs express their un- certainty? an empirical evaluation of confidence elicitation in LLMs. The Twelfth International Conference on Learning Representations.
  96. Junjielong Xu, Ruichun Yang, Yintong Huo, Chengyu Zhang, and Pinjia He. 2024. DivLog: Log parsing with prompt enhanced in-context learning. In Proceedings of the IEEE/ACM 46th International Conference on Software Engineering. 1-12.
  97. Senming Yan, Lei Shi, Jing Ren, Wei Wang, Yaxin Liu, Limin Sun, Xiong Wang, and Wei Zhang. 2024. Log-based anomaly detection with transformers pre-trained on large-scale unlabeled data. In Proceedings of the ICC 2024-IEEE International Conference on Communications. IEEE, 1-6.
  98. Jiexia Ye, Weiqi Zhang, Ke Yi, Yongzi Yu, Ziyue Li, Jia Li, and Fugee Tsung. 2024. A survey of time series foundation models: Generalizing time series representation with large language model. arXiv:2405.02358. Retrieved from https: //arxiv.org/abs/2405.02358 or https://api.semanticscholar.org/CorpusID:269605992 · arXiv
  99. Zhaoyang Yu, Minghua Ma, Chaoyun Zhang, Si Qin, Yu Kang, Chetan Bansal, Saravan Rajmohan, Yingnong Dang, Changhua Pei, Dan Pei, et al. 2024. Monitorassistant: Simplifying cloud service monitoring via large language mod- els. In Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering. 38-49.
  100. Yue Yuan, Wenchang Shi, Bin Liang, and Bo Qin. 2019. An approach to cloud execution failure diagnosis based on exception logs in openstack. In Proceedings of the 2019 IEEE 12th International Conference on Cloud Computing. IEEE, 124-131.
  101. Zhengran Zeng, Yuqun Zhang, Yong Xu, Minghua Ma, Bo Qiao, Wentao Zou, Qingjun Chen, Meng Zhang, Xu Zhang, Hongyu Zhang, et al. 2023. Traceark: Towards actionable performance anomaly alerting for online service systems. In Proceedings of the 2023 IEEE/ACM 45th International Conference on Software Engineering: Software Engineering in Practice. IEEE, 258-269.
  102. Dylan Zhang, Xuchao Zhang, Chetan Bansal, Pedro Las-Casas, Rodrigo Fonseca, and Saravan Rajmohan. 2024. LM- PACE: Confidence estimation by large language models for effective root causing of cloud incidents. In Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering. 388-398.
  103. Ke Zhang, Chenxi Zhang, Xin Peng, and Chaofeng Sha. 2022. Putracead: Trace anomaly detection with partial labels based on gnn and pu learning. In Proceedings of the 2022 IEEE 33rd International Symposium on Software Reliability Engineering. IEEE, 239-250.
  104. Lingzhe Zhang, Tong Jia, Mengxi Jia, Ying Li, Yong Yang, and Zhonghai Wu. 2024. Multivariate Log-based anomaly detection for distributed database. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 4256-4267.
  105. Lingzhe Zhang, Tong Jia, Mengxi Jia, Yifan Wu, Hongyi Liu, and Ying Li. 2025. ScalaLog: Scalable log-based failure diagnosis using LLM. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, 1-5.
  106. Lingzhe Zhang, Tong Jia, Mengxi Jia, Yifan Wu, Hongyi Liu, and Ying Li. 2025. XRAGLog: A resource-efficient and context-aware log-based anomaly detection method using retrieval-augmented generation. In Proceedings of the Workshop on Preventing and Detecting LLM Misinformation.
  107. Lingzhe Zhang, Yunpeng Zhai, Tong Jia, Chiming Duan, Siyu Yu, Jinyang Gao, Bolin Ding, Zhonghai Wu, and Ying Li. 2025. ThinkFL: Self-refining failure localization for microservice systems via reinforcement fine-tuning. arXiv preprint arXiv:2504.18776. · arXiv
  108. Lingzhe Zhang, Yunpeng Zhai, Tong Jia, Xiaosong Huang, Chiming Duan, and Ying Li. 2025. AgentFM: Role-aware failure management for distributed databases with LLM-driven multi-agents. arXiv preprint arXiv:2504.06614. · arXiv
  109. Mingyang Zhang, Jianfei Chen, Jianyi Liu, Jingchu Wang, Rui Shi, and Hua Sheng. 2022. LogST: Log semi-supervised anomaly detection based on sentence-BERT. In Proceedings of the 2022 7th International Conference on Signal and Image Processing. IEEE, 356-361.
  110. Shenglin Zhang, Yuhe Ji, Jiaqi Luan, Xiaohui Nie, Ziang Chen, Minghua Ma, Yongqian Sun, and Dan Pei. 2024. End- to-end automl for unsupervised log anomaly detection. In Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering. 1680-1692.
  111. Shenglin Zhang, Pengtian Zhu, Minghua Ma, Jiagang Wang, Yongqian Sun, Dongwen Li, Jingyu Wang, Qianying Guo, Xiaolei Hua, Lin Zhu, et al. 2024. Enhanced fine-tuning of lightweight domain-specific Q&A model based on large language models. In Proceedings of the 2024 IEEE 35th International Symposium on Software Reliability Engineering Workshops. IEEE, 61-66.
  112. Ting Zhang, Xin Huang, Wen Zhao, Shaohuang Bian, and Peng Du. 2023. LogPrompt: A log-based anomaly detec- tion framework using prompts. In Proceedings of the 2023 International Joint Conference on Neural Networks. IEEE, 1-8.
  113. Wei Zhang, Xianfu Cheng, Yi Zhang, Jian Yang, Hongcheng Guo, Zhoujun Li, Xiaolin Yin, Xiangyuan Guan, Xu Shi, and Liangfan Zheng. 2024. Eclipse: Semantic entropy-lcs for cross-lingual industrial log parsing. arXiv preprint arXiv:2405.13548. · arXiv
  114. Wei Zhang, Hongcheng Guo, Jian Yang, Yi Zhang, Chaoran Yan, Zhoujin Tian, Hangyuan Ji, Zhoujun Li, Tongliang Li, and TieqiaoZheng. 2024. mABC: Multi-agent blockchain-inspired collaboration for root cause analysis in micro- services architecture. Findings of the Association for Computational Linguistics: EMNLP 2024. 4017-4033.
  115. Wanhao Zhang, Qianli Zhang, Enyu Yu, Yuxiang Ren, Yeqing Meng, Mingxi Qiu, and Jilong Wang. 2024. LogRAG: Semi-supervised log-based anomaly detection with retrieval-augmented generation. In Proceedings of the 2024 IEEE International Conference on Web Services. IEEE, 1100-1102.
  116. Xuchao Zhang, Supriyo Ghosh, Chetan Bansal, Rujia Wang, Minghua Ma, Yu Kang, and Saravan Rajmohan. 2024. Automated root causing of cloud incidents using in-context learning with gpt-4. In Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering. 266-277.
  117. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, and Zican Dong. 2023. A survey of large language models. 1, 2 (2023). arXiv preprint arXiv:2303.18223. · arXiv
  118. Aoxiao Zhong, Dengyao Mo, Guiyang Liu, Jinbu Liu, Qingda Lu, Qi Zhou, Jiesheng Wu, Quanzheng Li, and Qingsong Wen. 2024. Logparser-LLM: Advancing efficient log parsing with large language models. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 4559-4570.
  119. Huazhen Zhong, Jibin Wang, Xuejian Wang, Xin Wang, Wenjie Xiao, Xuehai Tang, and Liangjun Zang. 2024. DBPrompt: A database anomaly operation detection and analysis via prompt learning. In Proceedings of the Interna- tional Conference on Intelligent Computing. Springer, 357-368.
  120. T. Zhou, P. Niu, L. Sun, and R. Ji. 2023. One fits all: Power general time series analysis by pretrained lm. Advances in Neural Information Processing Systems 36 (2023), 43322-43355.
  121. Xuanhe Zhou, Lianyuan Jin, Ji Sun, Xinyang Zhao, Xiang Yu, Jianhua Feng, Shifu Li, Tianqing Wang, Kun Li, and Luyang Liu. 2021. Dbmind: A self-driving platform in opengauss. Proceedings of the VLDB Endowment 14, 12 (2021), 2743-2746.
  122. Xuanhe Zhou, Guoliang Li, Zhaoyan Sun, Zhiyuan Liu, Weize Chen, Jianming Wu, Jiesi Liu, Ruohang Feng, and Guoyang Zeng. 2024. D-bot: database diagnosis system using large language models. Proceedings of the VLDB En- dowment 17, 10 (2024), 2514-2527.
  123. Xuanhe Zhou, Xinyang Zhao, and Guoliang Li. 2024. LLM-enhanced data management. arXiv preprint arXiv:2402.02643. · arXiv

Cited by

Sorted by citations

Related

Authors
Zhang, L., Jia, T., Jia, M., Wu, Y., Liu, A., Yang, Y., Wu, Z., Hu, X., Yu, P., & Li, Y.
Affiliations
  • Peking University (CN)
  • Tsinghua University (CN)
  • Hong Kong University of Science and Technology (HK)
  • University of Illinois Chicago (US)
ORCID
Venue
ACM Computing Surveys
Publisher
Association for Computing Machinery (ACM)
Published
2025-09-09
Volume
58
Issue
2
Pages
1-35
ISSN
  • 0360-0300 (ISSN-L)
  • 1557-7341
DOI
10.1145/3746635
OpenAlex
W4411735779
Cited by
49
References
60
Citations by year
2026: 43 · 2025: 6
FWCI
20.57
Type
journal article
Language
en
Open access
Locations
  • ACM Computing Surveys (publishedVersion)
  • arXiv (Cornell University) (publishedVersion)
  • arXiv (Cornell University)
Funders
National Key R&D Research Fund of China (2021YFF0704202)
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
AIOps, large language models, IT operations, evaluation methodology, research trends

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