{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T14:20:19Z","timestamp":1784989219427,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,21]]},"DOI":"10.1145\/3627673.3680016","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:11Z","timestamp":1729452851000},"page":"4966-4974","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":70,"title":["RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5779-9049","authenticated-orcid":false,"given":"Zefan","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8035-1991","authenticated-orcid":false,"given":"Zichuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1574-922X","authenticated-orcid":false,"given":"Yingying","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7584-5476","authenticated-orcid":false,"given":"Aoxiao","family":"Zhong","sequence":"additional","affiliation":[{"name":"Havard Univerrsity, Cambridge, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2529-3244","authenticated-orcid":false,"given":"Jihong","family":"Wang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3864-2849","authenticated-orcid":false,"given":"Fengbin","family":"Yin","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1865-6731","authenticated-orcid":false,"given":"Lunting","family":"Fan","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8081-6275","authenticated-orcid":false,"given":"Lingfei","family":"Wu","sequence":"additional","affiliation":[{"name":"Anytime AI, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4516-2524","authenticated-orcid":false,"given":"Qingsong","family":"Wen","sequence":"additional","affiliation":[{"name":"Squirrel Ai Learning, Bellevue, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International Conference on Service-Oriented Computing. 137--149","author":"Aggarwal Pooja","year":"2020","unstructured":"Pooja Aggarwal, Ajay Gupta, Prateeti Mohapatra, Seema Nagar, Atri Mandal, Qing Wang, and Amit Paradkar. 2020. Localization of operational faults in cloud applications by mining causal dependencies in logs using golden signals. In International Conference on Service-Oriented Computing. 137--149."},{"key":"e_1_3_2_1_2_1","volume-title":"Recommending Root-Cause and Mitigation Steps for Cloud Incidents Using Large Language Models. In International Conference on Software Engineering. 1737--1749","author":"Ahmed Toufique","year":"2023","unstructured":"Toufique Ahmed, Supriyo Ghosh, Chetan Bansal, Thomas Zimmermann, Xuchao Zhang, and Saravan Rajmohan. 2023. Recommending Root-Cause and Mitigation Steps for Cloud Incidents Using Large Language Models. In International Conference on Software Engineering. 1737--1749."},{"key":"e_1_3_2_1_3_1","volume-title":"ACL workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization. 65--72","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In ACL workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization. 65--72."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2008\/10\/P10008"},{"key":"e_1_3_2_1_5_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. In Advances in Neural Information Processing Systems. 1877--1901."},{"key":"e_1_3_2_1_6_1","volume-title":"Yuanzhi Li, Scott Lundberg, et al.","author":"Bubeck S\u00e9bastien","year":"2023","unstructured":"S\u00e9bastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, et al. 2023. Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712 (2023)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00040"},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Software Engineering: Software Engineering in Practice. 111--120","author":"Chen Junjie","year":"2019","unstructured":"Junjie Chen, Xiaoting He, Qingwei Lin, Yong Xu, Hongyu Zhang, Dan Hao, Feng Gao, Zhangwei Xu, Yingnong Dang, and Dongmei Zhang. 2019. An empirical investigation of incident triage for online service systems. In International Conference on Software Engineering: Software Engineering in Practice. 111--120."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2016.2607739"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Yinfang Chen Huaibing Xie Minghua Ma Yu Kang Xin Gao Liu Shi Yunjie Cao Xuedong Gao Hao Fan Ming Wen et al. 2023. Empowering Practical Root Cause Analysis by Large Language Models for Cloud Incidents. arXiv preprint arXiv:2305.15778 (2023).","DOI":"10.1145\/3627703.3629553"},{"key":"e_1_3_2_1_11_1","volume-title":"AI for IT Operations (AIOps) on Cloud Platforms: Reviews, Opportunities and Challenges. arXiv preprint arXiv:2304.04661","author":"Cheng Qian","year":"2023","unstructured":"Qian Cheng, Doyen Sahoo, Amrita Saha, Wenzhuo Yang, Chenghao Liu, Gerald Woo, Manpreet Singh, Silvio Saverese, and Steven CH Hoi. 2023. AI for IT Operations (AIOps) on Cloud Platforms: Reviews, Opportunities and Challenges. arXiv preprint arXiv:2304.04661 (2023)."},{"key":"e_1_3_2_1_12_1","unstructured":"Peng Gao Jiaming Han Renrui Zhang Ziyi Lin Shijie Geng Aojun Zhou Wei Zhang Pan Lu Conghui He Xiangyu Yue et al. 2023. Llama-adapter v2: Parameter-efficient visual instruction model. arXiv preprint arXiv:2304.15010 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"Symposium on Cloud Computing. 126--141","author":"Ghosh Supriyo","year":"2022","unstructured":"Supriyo Ghosh, Manish Shetty, Chetan Bansal, and Suman Nath. 2022. How to fight production incidents? an empirical study on a large-scale cloud service. In Symposium on Cloud Computing. 126--141."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534113"},{"key":"e_1_3_2_1_15_1","unstructured":"Anders Hejlsberg Steve Lucco Daniel Rosenwasser Pierce Boggan Umesh Madan Mike Hopcroft and Gayathri Chandrasekaran. 2023. Introducing TypeChat. https:\/\/microsoft.github.io\/TypeChat\/blog\/introducing-typechat\/"},{"key":"e_1_3_2_1_16_1","volume-title":"Xpert: Empowering Incident Management with Query Recommendations via Large Language Models. arXiv preprint arXiv:2312.11988","author":"Jiang Yuxuan","year":"2023","unstructured":"Yuxuan Jiang, Chaoyun Zhang, Shilin He, Zhihao Yang, Minghua Ma, Si Qin, Yu Kang, Yingnong Dang, Saravan Rajmohan, Qingwei Lin, et al. 2023. Xpert: Empowering Incident Management with Query Recommendations via Large Language Models. arXiv preprint arXiv:2312.11988 (2023)."},{"key":"e_1_3_2_1_17_1","unstructured":"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. arXiv preprint arXiv:2305.18084 (2023)."},{"key":"e_1_3_2_1_18_1","volume-title":"ACL Workshop on Evaluating NLG Evaluation. 28--37","author":"Kane Hassan","year":"2020","unstructured":"Hassan Kane, Muhammed Yusuf Kocyigit, Ali Abdalla, Pelkins Ajanoh, and Mohamed Coulibali. 2020. NUBIA: NeUral based interchangeability assessor for text generation. In ACL Workshop on Evaluating NLG Evaluation. 28--37."},{"key":"e_1_3_2_1_19_1","volume-title":"Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa.","author":"Kojima Takeshi","year":"2022","unstructured":"Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. In Advances in Neural Information Processing Systems. 22199--22213."},{"key":"e_1_3_2_1_20_1","volume-title":"Efficient Memory Management for Large Language Model Serving with PagedAttention. In Symposium on Operating Systems Principles. 611--626","author":"Kwon Woosuk","year":"2023","unstructured":"Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph Gonzalez, Hao Zhang, and Ion Stoica. 2023. Efficient Memory Management for Large Language Model Serving with PagedAttention. In Symposium on Operating Systems Principles. 611--626."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510155"},{"key":"e_1_3_2_1_22_1","unstructured":"Patrick Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. In Advances in Neural Information Processing Systems. 9459--9474."},{"key":"e_1_3_2_1_23_1","volume-title":"API-Bank: A benchmark for tool-augmented llms. arXiv preprint arXiv:2304.08244","author":"Li Minghao","year":"2023","unstructured":"Minghao Li, Feifan Song, Bowen Yu, Haiyang Yu, Zhoujun Li, Fei Huang, and Yongbin Li. 2023. API-Bank: A benchmark for tool-augmented llms. arXiv preprint arXiv:2304.08244 (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"Towards General Text Embeddings with Multi-stage Contrastive Learning. arXiv preprint arXiv:2308.03281","author":"Li Zehan","year":"2023","unstructured":"Zehan Li, Xin Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, and Meishan Zhang. 2023. Towards General Text Embeddings with Multi-stage Contrastive Learning. arXiv preprint arXiv:2308.03281 (2023)."},{"key":"e_1_3_2_1_25_1","volume-title":"Training Socially Aligned Language Models in Simulated Human Society. arXiv preprint arXiv:2305.16960","author":"Liu Ruibo","year":"2023","unstructured":"Ruibo Liu, Ruixin Yang, Chenyan Jia, Ge Zhang, Denny Zhou, Andrew M Dai, Diyi Yang, and Soroush Vosoughi. 2023. Training Socially Aligned Language Models in Simulated Human Society. arXiv preprint arXiv:2305.16960 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"Agentbench: Evaluating llms as agents. arXiv preprint arXiv:2308.03688","author":"Liu Xiao","year":"2023","unstructured":"Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu, Hangliang Ding, Kaiwen Men, Kejuan Yang, et al. 2023. Agentbench: Evaluating llms as agents. arXiv preprint arXiv:2308.03688 (2023)."},{"key":"e_1_3_2_1_27_1","volume-title":"Devansh Arpit, et al.","author":"Liu Zhiwei","year":"2023","unstructured":"Zhiwei Liu, Weiran Yao, Jianguo Zhang, Le Xue, Shelby Heinecke, Rithesh Murthy, Yihao Feng, Zeyuan Chen, Juan Carlos Niebles, Devansh Arpit, et al. 2023. BOLAA: Benchmarking and orchestrating LLM-augmented autonomous agents. arXiv preprint arXiv:2308.05960 (2023)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3083715"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3558946"},{"key":"e_1_3_2_1_30_1","volume-title":"MTEB: Massive Text Embedding Benchmark. In European","author":"Muennighoff Niklas","year":"2023","unstructured":"Niklas Muennighoff, Nouamane Tazi, Lo\"ic Magne, and Nils Reimers. 2023. MTEB: Massive Text Embedding Benchmark. In European Chapter of the Association for Computational Linguistics. 2006--2029."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2013.26"},{"key":"e_1_3_2_1_32_1","unstructured":"OpenAI. 2022. OpenAI: Introducing ChatGPT. https:\/\/openai.com\/blog\/chatgpt"},{"key":"e_1_3_2_1_34_1","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray et al. 2022. Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems. 27730--27744."},{"key":"e_1_3_2_1_35_1","volume-title":"Giraffe: Adventures in Expanding Context Lengths in LLMs. arXiv preprint arXiv:2308.10882","author":"Pal Arka","year":"2023","unstructured":"Arka Pal, Deep Karkhanis, Manley Roberts, Samuel Dooley, Arvind Sundararajan, and Siddartha Naidu. 2023. Giraffe: Adventures in Expanding Context Lengths in LLMs. arXiv preprint arXiv:2308.10882 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"Percy Liang, and Michael S Bernstein.","author":"Park Joon Sung","year":"2023","unstructured":"Joon Sung Park, Joseph C O'Brien, Carrie J Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. arXiv preprint arXiv:2304.03442 (2023)."},{"key":"e_1_3_2_1_37_1","unstructured":"Yujia Qin Shengding Hu Yankai Lin Weize Chen Ning Ding Ganqu Cui Zheni Zeng Yufei Huang Chaojun Xiao Chi Han et al. 2023. Tool learning with foundation models. arXiv preprint arXiv:2304.08354 (2023)."},{"key":"e_1_3_2_1_38_1","volume-title":"Toolllm: Facilitating large language models to master 16000 real-world apis. arXiv preprint arXiv:2307.16789","author":"Qin Yujia","year":"2023","unstructured":"Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, et al. 2023. Toolllm: Facilitating large language models to master 16000 real-world apis. arXiv preprint arXiv:2307.16789 (2023)."},{"key":"e_1_3_2_1_39_1","volume-title":"TPTU: Task planning and tool usage of large language model-based AI agents. arXiv preprint arXiv:2308.03427","author":"Ruan Jingqing","year":"2023","unstructured":"Jingqing Ruan, Yihong Chen, Bin Zhang, Zhiwei Xu, Tianpeng Bao, Guoqing Du, Shiwei Shi, Hangyu Mao, Xingyu Zeng, and Rui Zhao. 2023. TPTU: Task planning and tool usage of large language model-based AI agents. arXiv preprint arXiv:2308.03427 (2023)."},{"key":"e_1_3_2_1_40_1","volume-title":"Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom.","author":"Schick Timo","year":"2023","unstructured":"Timo Schick, Jane Dwivedi-Yu, Roberto Dess`i, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. Toolformer: Language models can teach themselves to use tools. arXiv preprint arXiv:2302.04761 (2023)."},{"key":"e_1_3_2_1_41_1","volume-title":"BLEURT: Learning robust metrics for text generation","author":"Sellam Thibault","year":"2020","unstructured":"Thibault Sellam, Dipanjan Das, and Ankur Parikh. 2020. BLEURT: Learning robust metrics for text generation. In Association for Computational Linguistics. 7881--7892."},{"key":"e_1_3_2_1_42_1","volume-title":"Reflexion: Language Agents with Verbal Reinforcement Learning. In Advances in Neural Information Processing Systems.","author":"Shinn Noah","year":"2023","unstructured":"Noah Shinn, Federico Cassano, Edward Berman, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: Language Agents with Verbal Reinforcement Learning. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_43_1","unstructured":"Significant-Gravitas. 2023. AutoGPT: the heart of the open-source agent ecosystem. https:\/\/github. com\/Significant-Gravitas\/Auto-GPT. GitHub repository."},{"key":"e_1_3_2_1_44_1","volume-title":"Cognitive architectures for language agents. arXiv preprint arXiv:2309.02427","author":"Sumers Theodore","year":"2023","unstructured":"Theodore Sumers, Shunyu Yao, Karthik Narasimhan, and Thomas L Griffiths. 2023. Cognitive architectures for language agents. arXiv preprint arXiv:2309.02427 (2023)."},{"key":"e_1_3_2_1_45_1","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. arxiv: 2302.13971"},{"key":"e_1_3_2_1_46_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. LLaMA 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"Lei Wang Chen Ma Xueyang Feng Zeyu Zhang Hao Yang Jingsen Zhang Zhiyuan Chen Jiakai Tang Xu Chen Yankai Lin et al. 2023. A survey on large language model based autonomous agents. arXiv preprint arXiv:2308.11432 (2023).","DOI":"10.1007\/s11704-024-40231-1"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS49710.2020.00026"},{"key":"e_1_3_2_1_50_1","volume-title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models. In International Conference on Learning Representations. 1--24","author":"Wang Xuezhi","year":"2023","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023. Self-Consistency Improves Chain of Thought Reasoning in Language Models. In International Conference on Learning Representations. 1--24."},{"key":"e_1_3_2_1_51_1","volume-title":"Xiuying Chen, et al.","author":"Wang Zekun","year":"2023","unstructured":"Zekun Wang, Ge Zhang, Kexin Yang, Ning Shi, Wangchunshu Zhou, Shaochun Hao, Guangzheng Xiong, Yizhi Li, Mong Yuan Sim, Xiuying Chen, et al. 2023. Interactive natural language processing. arXiv preprint arXiv:2305.13246 (2023)."},{"key":"e_1_3_2_1_52_1","unstructured":"Jason Wei Yi Tay Rishi Bommasani Colin Raffel Barret Zoph Sebastian Borgeaud Dani Yogatama Maarten Bosma Denny Zhou Donald Metzler et al. 2022. Emergent Abilities of Large Language Models. Transactions on Machine Learning Research (2022) 1--30."},{"key":"e_1_3_2_1_53_1","volume-title":"Efficient Guided Generation for Large Language Models. arXiv e-prints","author":"Willard Brandon T","year":"2023","unstructured":"Brandon T Willard and R\u00e9mi Louf. 2023. Efficient Guided Generation for Large Language Models. arXiv e-prints (2023), arXiv--2307."},{"key":"e_1_3_2_1_54_1","unstructured":"Zhiheng Xi Wenxiang Chen Xin Guo Wei He Yiwen Ding Boyang Hong Ming Zhang Junzhe Wang Senjie Jin Enyu Zhou et al. 2023. The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864 (2023)."},{"key":"e_1_3_2_1_55_1","volume-title":"ReAct: Synergizing Reasoning and Acting in Language Models. In International Conference on Learning Representations. 1--33","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. 2023. ReAct: Synergizing Reasoning and Acting in Language Models. In International Conference on Learning Representations. 1--33."},{"key":"e_1_3_2_1_56_1","unstructured":"yoheinakajima. 2023. BabyAgi. https:\/\/github.com\/yoheinakajima\/babyagi. GitHub repository."},{"key":"e_1_3_2_1_57_1","first-page":"27263","article-title":"Bartscore: Evaluating generated text as text generation","volume":"34","author":"Yuan Weizhe","year":"2021","unstructured":"Weizhe Yuan, Graham Neubig, and Pengfei Liu. 2021. Bartscore: Evaluating generated text as text generation. In Advances in Neural Information Processing Systems, Vol. 34. 27263--27277.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557470"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747882"},{"key":"e_1_3_2_1_60_1","volume-title":"PACE: Prompting and Augmentation for Calibrated Confidence Estimation with GPT-4 in Cloud Incident Root Cause Analysis. arXiv preprint arXiv:2309.05833","author":"Zhang Dylan","year":"2023","unstructured":"Dylan Zhang, Xuchao Zhang, Chetan Bansal, Pedro Las-Casas, Rodrigo Fonseca, and Saravan Rajmohan. 2023. PACE: Prompting and Augmentation for Calibrated Confidence Estimation with GPT-4 in Cloud Incident Root Cause Analysis. arXiv preprint arXiv:2309.05833 (2023)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481903"},{"key":"e_1_3_2_1_62_1","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric Xing et al. 2023. Judging LLM-as-a-judge with MT-Bench and Chatbot Arena. arXiv preprint arXiv:2306.05685 (2023)."},{"key":"e_1_3_2_1_63_1","volume-title":"Llm as dba. arXiv preprint arXiv:2308.05481","author":"Zhou Xuanhe","year":"2023","unstructured":"Xuanhe Zhou, Guoliang Li, and Zhiyuan Liu. 2023. Llm as dba. arXiv preprint arXiv:2308.05481 (2023)."}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","location":"Boise ID USA","acronym":"CIKM '24","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3680016","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3680016","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:17Z","timestamp":1750294697000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3680016"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":61,"alternative-id":["10.1145\/3627673.3680016","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3680016","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}