{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:24:29Z","timestamp":1792513469138,"version":"4.5.0"},"reference-count":88,"publisher":"Association for Computing Machinery (ACM)","issue":"9","license":[{"start":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T00:00:00Z","timestamp":1787270400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Key-Area Research and Development Program of Guangdong Province, China","award":["No. 2020B010164003"],"award-info":[{"award-number":["No. 2020B010164003"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2026,9,30]]},"abstract":"<jats:p>\n                    As modern microservice systems grow increasingly popular and complex\u2014often consisting of hundreds or even thousands of interdependent components\u2014they are becoming more susceptible to frequent and subtle failures. Ensuring system reliability therefore hinges on accurate and efficient failure localization. Traditional failure localization approaches based on small models lack the flexibility to adapt to diverse failure scenarios, while recent LLM-based methods suffer from two major limitations: they often rely on rigid invocation workflows that constrain the model\u2019s ability to dynamically explore effective localization paths, and they require resource-intensive inference, making them cost-prohibitive for real-world deployment. To address these challenges, we explore the use of reinforcement fine-tuning to equip lightweight LLMs with reasoning and self-refinement capabilities, significantly improving the cost-effectiveness and adaptability of LLM-based failure localization. We begin with an empirical study to identify three key capabilities essential for accurate localization. Building on these insights, we propose a progressive multi-stage GRPO fine-tuning framework, which integrates a multi-factor failure localization grader and a recursion-of-thought actor module. The resulting model,\n                    <jats:italic toggle=\"yes\">ThinkFL<\/jats:italic>\n                    , not only outperforms existing state-of-the-art LLMs and baseline methods in localization accuracy but also reduces end-to-end localization latency from minutes to seconds, demonstrating strong potential for real-world applications.\n                  <\/jats:p>","DOI":"10.1145\/3789262","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T14:49:24Z","timestamp":1768834164000},"page":"1-44","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["ThinkFL: Self-Refining Failure Localization for Microservice Systems via Reinforcement Fine-Tuning"],"prefix":"10.1145","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9500-4489","authenticated-orcid":false,"given":"Lingzhe","family":"Zhang","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3344-4543","authenticated-orcid":false,"given":"Yunpeng","family":"Zhai","sequence":"additional","affiliation":[{"name":"Alibaba Group, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5946-9829","authenticated-orcid":false,"given":"Tong","family":"Jia","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China and National Key Laboratory of Data Space Technology and\u00a0System, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4422-6323","authenticated-orcid":false,"given":"Chiming","family":"Duan","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3793-7684","authenticated-orcid":false,"given":"Siyu","family":"Yu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2094-3554","authenticated-orcid":false,"given":"Jinyang","family":"Gao","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1535-9692","authenticated-orcid":false,"given":"Bolin","family":"Ding","sequence":"additional","affiliation":[{"name":"Alibaba Group, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1268-836X","authenticated-orcid":false,"given":"Zhonghai","family":"Wu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6278-2357","authenticated-orcid":false,"given":"Ying","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,21]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Afra Amini Tim Vieira and Ryan Cotterell. 2024. Direct preference optimization with an offset. arXiv:2402.10571. Retrieved from https:\/\/arxiv.org\/abs\/2402.10571","DOI":"10.18653\/v1\/2024.findings-acl.592"},{"key":"e_1_3_2_3_2","volume-title":"The Site Reliability Workbook: Practical Ways to Implement SRE","author":"Beyer Betsy","year":"2018","unstructured":"Betsy Beyer, Niall Richard Murphy, David K. Rensin, Kent Kawahara, and Stephen Thorne. 2018. The Site Reliability Workbook: Practical Ways to Implement SRE. O\u2019Reilly Media, Inc."},{"key":"e_1_3_2_4_2","unstructured":"Ching Chang Wen-Chih Peng and Tien-Fu Chen. 2023. Llm4ts: Two-stage fine-tuning for time-series forecasting with pre-trained llms. arXiv:2308.08469. Retrieved from https:\/\/arxiv.org\/abs\/2308.08469"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629553"},{"key":"e_1_3_2_6_2","first-page":"4302","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano Paul F.","year":"2017","unstructured":"Paul F. Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. Advances in Neural Information Processing Systems 30 (2017), 4302\u20134310.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.5555\/3692070.3692474"},{"key":"e_1_3_2_8_2","first-page":"29996","article-title":"Simmtm: A simple pre-training framework for masked time-series modeling","volume":"36","author":"Dong Jiaxiang","year":"2024","unstructured":"Jiaxiang Dong, Haixu Wu, Haoran Zhang, Li Zhang, Jianmin Wang, and Mingsheng Long. 2024. Simmtm: A simple pre-training framework for masked time-series modeling. Advances in Neural Information Processing Systems 36 (2024), 29996\u201330025.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_9_2","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv:2407.21783. Retrieved from https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_2_10_2","unstructured":"Sicheng Feng Gongfan Fang Xinyin Ma and Xinchao Wang. 2025. Efficient reasoning models: A survey. arXiv:2504.10903. Retrieved from https:\/\/arxiv.org\/abs\/2504.10903"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446700"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304004"},{"key":"e_1_3_2_13_2","first-page":"292","volume-title":"Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","author":"Gu Jiazhen","year":"2020","unstructured":"Jiazhen Gu, Chuan Luo, Si Qin, Bo Qiao, Qingwei Lin, Hongyu Zhang, Ze Li, Yingnong Dang, Shaowei Cai, Wei Wu, et al. 2020. Efficient incident identification from multi-dimensional issue reports via meta-heuristic search. In Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 292\u2013303."},{"key":"e_1_3_2_14_2","first-page":"403","volume-title":"2024 IEEE 35th International Symposium on Software Reliability Engineering (ISSRE)","author":"Gu Wenwei","year":"2024","unstructured":"Wenwei Gu, Xinying Sun, Jinyang Liu, Yintong Huo, Zhuangbin Chen, Jianping Zhang, Jiazhen Gu, Yongqiang Yang, and Michael R. Lyu. 2024. KPIRoot: Efficient monitoring metric-based root cause localization in large-scale cloud systems. In 2024 IEEE 35th International Symposium on Software Reliability Engineering (ISSRE). IEEE, 403\u2013414."},{"key":"e_1_3_2_15_2","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv:2501.12948. Retrieved from https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"e_1_3_2_16_2","unstructured":"Hongcheng Guo Jian Yang Jiaheng Liu Liqun Yang Linzheng Chai Jiaqi Bai Junran Peng Xiaorong Hu Chao Chen Dongfeng Zhang et al. 2023. Owl: A large language model for it operations. arXiv:2309.09298. Retrieved from https:\/\/arxiv.org\/abs\/2309.09298"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3691620.3695475"},{"key":"e_1_3_2_18_2","unstructured":"Jian Hu Xibin Wu Zilin Zhu Weixun Wang Dehao Zhang and Yu Cao. 2024. Openrlhf: An easy-to-use scalable and high-performance rlhf framework. arXiv:2405.11143. Retrieved from https:\/\/arxiv.org\/abs\/2405.11143"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-024-00843-2"},{"key":"e_1_3_2_20_2","first-page":"3081","volume-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Jia Tong","year":"2022","unstructured":"Tong Jia, Ying Li, Yong Yang, Gang Huang, and Zhonghai Wu. 2022. Augmenting log-based anomaly detection models to reduce false anomalies with human feedback. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 3081\u20133089."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639081"},{"issue":"2","key":"e_1_3_2_22_2","first-page":"1","article-title":"PreLog: A pre-trained model for log analytics","volume":"3","author":"Le Van-Hoang","year":"2024","unstructured":"Van-Hoang Le and Hongyu Zhang. 2024. PreLog: A pre-trained model for log analytics. Proceedings of the ACM on Management of Data, 2, 3 (2024), 1\u201328.","journal-title":"Proceedings of the ACM on Management of Data"},{"key":"e_1_3_2_23_2","first-page":"1","article-title":"Enjoy your observability: An industrial survey of microservice tracing and analysis","volume":"27","author":"Li Bowen","year":"2022","unstructured":"Bowen Li, Xin Peng, Qilin Xiang, Hanzhang Wang, Tao Xie, Jun Sun, and Xuanzhe Liu. 2022. Enjoy your observability: An industrial survey of microservice tracing and analysis. Empirical Software Engineering 27 (2022), 1\u201328.","journal-title":"Empirical Software Engineering"},{"key":"e_1_3_2_24_2","unstructured":"Chen Li Nazhou Liu and Kai Yang. 2025. Adaptive group policy optimization: Towards stable training and token-efficient reasoning. arXiv:2503.15952. Retrieved from https:\/\/arxiv.org\/abs\/2503.15952"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539041"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE55347.2025.00234"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/IWQOS52092.2021.9521340"},{"key":"e_1_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Wenlong Liao Fernando Porte-Agel Jiannong Fang Christian Rehtanz Shouxiang Wang Dechang Yang and Zhe Yang. 2024. TimeGPT in load forecasting: A large time series model perspective. arXiv:2404.04885. Retrieved from https:\/\/arxiv.org\/abs\/2404.04885","DOI":"10.1016\/j.apenergy.2024.124973"},{"key":"e_1_3_2_29_2","first-page":"206","article-title":"Root cause analysis in microservice using neural granger causal discovery","author":"Lin Cheng-Ming","year":"2024","unstructured":"Cheng-Ming Lin, Ching Chang, Wei-Yao Wang, Kuang-Da Wang, and Wen-Chih Peng. 2024. Root cause analysis in microservice using neural granger causal discovery. In Proceedings of the 38th AAAI Conference on Artificial Intelligence, 206\u2013213.","journal-title":"Proceedings of the 38th AAAI Conference on Artificial Intelligence"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-03596-9_1"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/2884781.2884795"},{"key":"e_1_3_2_32_2","unstructured":"Zhihang Lin Mingbao Lin Yuan Xie and Rongrong Ji. 2025. Cppo: Accelerating the training of group relative policy optimization-based reasoning models. arXiv:2503.22342. Retrieved from https:\/\/arxiv.org\/abs\/2503.22342"},{"key":"e_1_3_2_33_2","unstructured":"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. arXiv:2402.16132. Retrieved from https:\/\/arxiv.org\/abs\/2402.16132"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE5003.2020.00014"},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Shuo Liu Di Yao Lanting Fang Zhetao Li Wenbin Li Kaiyu Feng XiaoWen Ji and Jingping Bi. 2024. Anomalyllm: Few-shot anomaly edge detection for dynamic graphs using large language models. arXiv:2405.07626. Retrieved from https:\/\/arxiv.org\/abs\/2405.07626","DOI":"10.1109\/ICDM59182.2024.00093"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645434"},{"key":"e_1_3_2_37_2","unstructured":"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:2410.09352. Retrieved from https:\/\/arxiv.org\/abs\/2410.09352"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643916.3644408"},{"key":"e_1_3_2_39_2","first-page":"32369","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Liu Yong","year":"2024","unstructured":"Yong Liu, Haoran Zhang, Chenyu Li, Xiangdong Huang, Jianmin Wang, and Mingsheng Long. 2024. Timer: Generative pre-trained transformers are large time series models. In Proceedings of the 41st International Conference on Machine Learning, 32369\u201332399."},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3487003"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICST.2018.00034"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/WFPST58552.2024.00034"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3715225"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"key":"e_1_3_2_45_2","unstructured":"Kashif Rasul Arjun Ashok Andrew Robert Williams Arian Khorasani George Adamopoulos Rishika Bhagwatkar Marin Bilo\u0161 Hena Ghonia Nadhir Hassen Anderson Schneider et al. 2023. Lag-llama: Towards foundation models for time series forecasting. arXiv:2310.08278. Retrieved from https:\/\/arxiv.org\/abs\/2310.08278"},{"key":"e_1_3_2_46_2","unstructured":"Rui Ren. 2025. The multi-agent fault localization system based on Monte Carlo tree search approach. arXiv:2507.22800. Retrieved from https:\/\/arxiv.org\/abs\/2507.22800"},{"key":"e_1_3_2_47_2","unstructured":"Soham Sane. 2025. Hybrid group relative policy optimization: a multi-sample approach to enhancing policy optimization. arXiv:2502.01652. Retrieved from https:\/\/arxiv.org\/abs\/2502.01652"},{"key":"e_1_3_2_48_2","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv:1707.06347. Retrieved from https:\/\/arxiv.org\/abs\/1707.06347"},{"key":"e_1_3_2_49_2","unstructured":"Zhihong Shao Peiyi Wang Qihao Zhu Runxin Xu Junxiao Song Xiao Bi Haowei Zhang Mingchuan Zhang Y. K. Li Y. Wu et al. 2024. Deepseekmath: Pushing the limits of mathematical reasoning in open language model. arXiv:2402.03300. Retrieved from https:\/\/arxiv.org\/abs\/2402.03300"},{"key":"e_1_3_2_50_2","unstructured":"Zhuocheng Shen. 2024. Llm with tools: A survey. arXiv:2409.18807. Retrieved from https:\/\/arxiv.org\/abs\/2409.18807"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE59848.2023.00082"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3695999"},{"key":"e_1_3_2_53_2","unstructured":"Yifang Tian Yaming Liu Zichun Chong Zihang Huang and Hans-Arno Jacobsen. 2025. GALA: Can graph-augmented large language model agentic workflows elevate root cause analysis? arXiv:2508.12472. Retrieved from https:\/\/arxiv.org\/abs\/2508.12472"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599934"},{"key":"e_1_3_2_55_2","unstructured":"Qi Wang Xiao Zhang Mingyi Li Yuan Yuan Mengbai Xiao Fuzhen Zhuang and Dongxiao Yu. 2025. TAMO: Fine-grained root cause analysis via tool-assisted llm agent with multi-modality observation data in cloud-native systems. arXiv:2504.20462. Retrieved from https:\/\/arxiv.org\/abs\/2504.20462"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3691620.3695485"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3680016"},{"key":"e_1_3_2_58_2","doi-asserted-by":"crossref","first-page":"111061","DOI":"10.1016\/j.jss.2021.111061","article-title":"Design, monitoring, and testing of microservices systems: The practitioners\u2019 perspective","volume":"182","author":"Waseem Muhammad","year":"2021","unstructured":"Muhammad Waseem, Peng Liang, Mojtaba Shahin, Amleto Di Salle, and Gast\u00f3n M\u00e1rquez. 2021. Design, monitoring, and testing of microservices systems: The practitioners\u2019 perspective. Journal of Systems and Software 182 (2021), 111061.","journal-title":"Journal of Systems and Software"},{"key":"e_1_3_2_59_2","volume-title":"The 13th International Conference on Learning Representations","author":"Wu Yangzhen","year":"2025","unstructured":"Yangzhen Wu, Zhiqing Sun, Shanda Li, Sean Welleck, and Yiming Yang. 2025. Inference scaling laws: An empirical analysis of compute-optimal inference for LLM problem-solving. In The 13th International Conference on Learning Representations."},{"key":"e_1_3_2_60_2","unstructured":"Yong Xiang Charley Peter Chen Liyi Zeng Wei Yin Xin Liu Hu Li and Wei Xu. 2025. Simplifying root cause analysis in kubernetes with stateGraph and LLM. arXiv:2506.02490. Retrieved from https:\/\/arxiv.org\/abs\/2506.02490"},{"key":"e_1_3_2_61_2","volume-title":"The 13th International Conference on Learning Representations","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 The 13th International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=M4qNIzQYpd"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3342137"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539109"},{"key":"e_1_3_2_64_2","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et al. 2025. Qwen3 technical report. arXiv:2505.09388. Retrieved from https:\/\/arxiv.org\/abs\/2505.09388"},{"key":"e_1_3_2_65_2","unstructured":"Boyang Yang Zijian Cai Fengling Liu Bach Le Lingming Zhang Tegawend\u00e9 F. Bissyand\u00e9 Yang Liu and Haoye Tian. 2025. A survey of LLM-based automated program repair: Taxonomies design paradigms and applications. arXiv:2506.23749. Retrieved from https:\/\/arxiv.org\/abs\/2506.23749"},{"key":"e_1_3_2_66_2","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1109\/ASE51524.2021.9678534","volume-title":"2021 36th IEEE\/ACM International Conference on Automated Software Engineering (ASE)","author":"Yang Tianyi","year":"2021","unstructured":"Tianyi Yang, Jiacheng Shen, Yuxin Su, Xiao Ling, Yongqiang Yang, and Michael R. Lyu. 2021. AID: Efficient prediction of aggregated intensity of dependency in large-scale cloud systems. In 2021 36th IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE, 653\u2013665."},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663529.3663827"},{"key":"e_1_3_2_68_2","doi-asserted-by":"crossref","first-page":"18287","DOI":"10.18653\/v1\/2025.acl-long.895","volume-title":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"YifeiLu YifeiLu","year":"2025","unstructured":"YifeiLu YifeiLu, Fanghua Ye, Jian Li, Qiang Gao, Cheng Liu, Haibo Luo, Nan Du, Xiaolong Li, and Feiliang Ren. 2025. CodeTool: Enhancing programmatic tool invocation of LLMs via process supervision. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 18287\u201318304."},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2619715"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449905"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616249"},{"issue":"10","key":"e_1_3_2_72_2","first-page":"e2413","article-title":"TraceRank: Abnormal service localization with dis-aggregated end-to-end tracing data in cloud native systems","volume":"35","author":"Yu Guangba","year":"2023","unstructured":"Guangba Yu, Zicheng Huang, and Pengfei Chen. 2023. TraceRank: Abnormal service localization with dis-aggregated end-to-end tracing data in cloud native systems. Journal of Software: Evolution and Process 35, 10 (2023), e2413.","journal-title":"Journal of Software: Evolution and Process"},{"key":"e_1_3_2_73_2","first-page":"6190","volume-title":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Yu Zhaoyang","year":"2024","unstructured":"Zhaoyang Yu, Changhua Pei, Xin Wang, Minghua Ma, Chetan Bansal, Saravan Rajmohan, Qingwei Lin, Dongmei Zhang, Xidao Wen, Jianhui Li, et al. 2024. Pre-trained kpi anomaly detection model through disentangled transformer. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 6190\u20136201."},{"key":"e_1_3_2_74_2","doi-asserted-by":"crossref","first-page":"951","DOI":"10.18653\/v1\/2025.naacl-long.44","volume-title":"Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","author":"Yuan Siyu","year":"2025","unstructured":"Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan, Yongliang Shen, Kan Ren, Dongsheng Li, and Deqing Yang. 2025. EASYTOOL: Enhancing LLM-based agents with concise tool instruction. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 951\u2013972."},{"key":"e_1_3_2_75_2","unstructured":"Yongcheng Zeng Guoqing Liu Weiyu Ma Ning Yang Haifeng Zhang and Jun Wang. 2024. Token-level direct preference optimization. arXiv:2404.11999. Retrieved from https:\/\/arxiv.org\/abs\/2404.11999"},{"key":"e_1_3_2_76_2","unstructured":"Yunpeng Zhai Shuchang Tao Cheng Chen Anni Zou Ziqian Chen Qingxu Fu Shinji Mai Li Yu Jiaji Deng Zouying Cao et al. 2025. AgentEvolver: Towards efficient self-evolving agent system. arXiv:2511.10395. Retrieved from https:\/\/arxiv.org\/abs\/2511.10395"},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639088"},{"key":"e_1_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663529.3663858"},{"key":"e_1_3_2_79_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3715318","article-title":"A survey of AIOps in the era of large language models","author":"Zhang Lingzhe","year":"2025","unstructured":"Lingzhe Zhang, Tong Jia, Mengxi Jia, Yifan Wu, Aiwei Liu, Yong Yang, Zhonghai Wu, Xuming Hu, Philip Yu, and Ying Li. 2025. A survey of AIOps in the era of large language models. ACM Computing Surveys 58, 2, Article 44 (2025), 1\u201335.","journal-title":"ACM Computing Surveys"},{"key":"e_1_3_2_80_2","unstructured":"Lingzhe Zhang Tong Jia Kangjin Wang Weijie Hong Chiming Duan Minghua He and Ying Li. 2025. Adaptive root cause localization for microservice systems with multi-agent recursion-of-thought. arXiv:2508.20370. Retrieved from https:\/\/arxiv.org\/abs\/2508.20370"},{"key":"e_1_3_2_81_2","unstructured":"Lingzhe Zhang Yunpeng Zhai Tong Jia Chiming Duan Minghua He Leyi Pan Zhaoyang Liu Bolin Ding and Ying Li. 2025. MicroRemed: Benchmarking LLMs in microservices remediation. arXiv:2511.01166. Retrieved from https:\/\/arxiv.org\/abs\/2511.01166"},{"key":"e_1_3_2_82_2","first-page":"738","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track","author":"Zhang Tianyang","year":"2024","unstructured":"Tianyang Zhang, Zhuoxuan Jiang, Shengguang Bai, Tianrui Zhang, Lin Lin, Yang Liu, and Jiawei Ren. 2024. RAG4ITOps: A supervised fine-tunable and comprehensive RAG framework for IT operations and maintenance. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, 738\u2013754."},{"key":"e_1_3_2_83_2","doi-asserted-by":"crossref","first-page":"4017","DOI":"10.18653\/v1\/2024.findings-emnlp.232","volume-title":"Findings of the Association for Computational Linguistics (EMNLP \u201924)","author":"Zhang Wei","year":"2024","unstructured":"Wei Zhang, Hongcheng Guo, Jian Yang, Zhoujin Tian, Yi Zhang, Yan Chaoran, Zhoujun Li, Tongliang Li, Xu Shi, Liangfan Zheng, et al. 2024. mABC: Multi-agent blockchain-inspired collaboration for root cause analysis in micro-services architecture. In Findings of the Association for Computational Linguistics (EMNLP \u201924), 4017\u20134033."},{"key":"e_1_3_2_84_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS62655.2024.00129"},{"key":"e_1_3_2_85_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467190"},{"key":"e_1_3_2_86_2","first-page":"655","volume-title":"2022 USENIX Annual Technical Conference (USENIX ATC 22)","author":"Zhang Zhizhou","year":"2022","unstructured":"Zhizhou Zhang, Murali Krishna Ramanathan, Prithvi Raj, Abhishek Parwal, Timothy Sherwood, and Milind Chabbi. 2022. \\(\\{\\) CRISP \\(\\}\\) : Critical path analysis of \\(\\{\\) Large-Scale \\(\\}\\) microservice architectures. In 2022 USENIX Annual Technical Conference (USENIX ATC 22), 655\u2013672."},{"key":"e_1_3_2_87_2","doi-asserted-by":"crossref","unstructured":"Weijie Zhou Yi Peng Manli Tao Chaoyang Zhao Honghui Dong Ming Tang and Jinqiao Wang. 2025. LightPlanner: Unleashing the reasoning capabilities of lightweight large language models in task planning. arXiv:2503.08508. Retrieved from https:\/\/arxiv.org\/abs\/2503.08508","DOI":"10.1109\/IROS60139.2025.11247436"},{"key":"e_1_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1145\/3338906.3338961"},{"key":"e_1_3_2_89_2","unstructured":"Daniel M. Ziegler Nisan Stiennon Jeffrey Wu Tom B. Brown Alec Radford Dario Amodei Paul Christiano and Geoffrey Irving. 2019. Fine-tuning language models from human preferences. arXiv:1909.08593. Retrieved from https:\/\/arxiv.org\/abs\/1909.08593"}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3789262","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T16:15:25Z","timestamp":1787328925000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3789262"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,21]]},"references-count":88,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,9,30]]}},"alternative-id":["10.1145\/3789262"],"URL":"https:\/\/doi.org\/10.1145\/3789262","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,21]]},"assertion":[{"value":"2025-04-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-05","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}