{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:09Z","timestamp":1786120809506,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["U23B2048"],"award-info":[{"award-number":["U23B2048"]}]},{"name":"National Natural Science Foundation of China","award":["U22B2037"],"award-info":[{"award-number":["U22B2037"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817982","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"3306-3317","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7840-9385","authenticated-orcid":false,"given":"Wei","family":"Liu","sequence":"first","affiliation":[{"name":"School of CS & Key Lab of High Confidence Software Technologies (MOE), Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7905-1182","authenticated-orcid":false,"given":"Yang","family":"Gu","sequence":"additional","affiliation":[{"name":"Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5637-0286","authenticated-orcid":false,"given":"Xi","family":"Yan","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9448-3430","authenticated-orcid":false,"given":"Zihan","family":"Nan","sequence":"additional","affiliation":[{"name":"School of Software & Microelectronics, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4178-2451","authenticated-orcid":false,"given":"Beicheng","family":"Xu","sequence":"additional","affiliation":[{"name":"School of CS & Key Lab of High Confidence Software Technologies (MOE), Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3298-9047","authenticated-orcid":false,"given":"Keyao","family":"Ding","sequence":"additional","affiliation":[{"name":"School of CS & Key Lab of High Confidence Software Technologies (MOE), Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1681-4677","authenticated-orcid":false,"given":"Bin","family":"Cui","sequence":"additional","affiliation":[{"name":"School of CS & Beijing Key Laboratory of Software and Hardware Cooperative Artificial Intelligence Systems, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7532-5550","authenticated-orcid":false,"given":"Wentao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Center for Machine Learning Research, Peking University, Beijing, China and Zhongguancun Academy, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the ICLR 2025 Workshop on Foundation Models in the Wild. https:\/\/arxiv.org\/abs\/2503","author":"Bendinelli Tommaso","year":"2025","unstructured":"Tommaso Bendinelli, Artur Dox, and Christian Holz. 2025. Exploring LLM Agents for Cleaning Tabular Machine Learning Datasets. In Proceedings of the ICLR 2025 Workshop on Foundation Models in the Wild. https:\/\/arxiv.org\/abs\/2503.06664 Preprint available at https:\/\/arxiv.org\/abs\/2503.06664."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Fabian Biester Mohamed Abdelaal and Daniel Del Gaudio. 2024. LLMClean: Context-Aware Tabular Data Cleaning via LLM-Generated OFDs. arXiv:2404.18681 [cs.DB] https:\/\/arxiv.org\/abs\/2404.18681","DOI":"10.1007\/978-3-031-70421-5_7"},{"key":"e_1_3_2_1_3_1","unstructured":"Zhicheng Ding Jiahao Tian Zhenkai Wang Jinman Zhao and Siyang Li. 2024. Data Imputation using Large Language Model to Accelerate Recommendation System. arXiv:2407.10078 [cs.IR] https:\/\/arxiv.org\/abs\/2407.10078"},{"key":"e_1_3_2_1_4_1","unstructured":"Jiajie Fu Haitong Tang Arijit Khan Sharad Mehrotra Xiangyu Ke and Yunjun Gao. 2025. In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Exploration. arXiv:2506.02509 [cs.DB] https:\/\/arxiv.org\/abs\/2506.02509"},{"key":"e_1_3_2_1_5_1","unstructured":"Yunfan Gao Yun Xiong Xinyu Gao Kangxiang Jia Jinliu Pan Yuxi Bi Yi Dai Jiawei Sun Meng Wang and Haofen Wang. 2024. Retrieval-Augmented Generation for Large Language Models: A Survey. arXiv:2312.10997 [cs.CL] https:\/\/arxiv.org\/abs\/2312.10997"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.361"},{"key":"e_1_3_2_1_7_1","volume-title":"Data Interpreter: An LLM Agent For Data Science. arXiv:2402.18679 [cs.AI] https:\/\/arxiv.org\/abs\/2402.18679","author":"Hong Sirui","year":"2024","unstructured":"Sirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu, Binhao Wu, Ceyao Zhang, Chenxing Wei, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Li Zhang, Lingyao Zhang, Min Yang, Mingchen Zhuge, Taicheng Guo, Tuo Zhou, Wei Tao, Xiangru Tang, Xiangtao Lu, Xiawu Zheng, Xinbing Liang, Yaying Fei, Yuheng Cheng, Zhibin Gou, Zongze Xu, and Chenglin Wu. 2024a. Data Interpreter: An LLM Agent For Data Science. arXiv:2402.18679 [cs.AI] https:\/\/arxiv.org\/abs\/2402.18679"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 12th International Conference on Learning Representations (ICLR 2024). https:\/\/arxiv.org\/abs\/2308.00352 Published as a conference paper at ICLR 2024. Preprint","author":"Hong Sirui","year":"2024","unstructured":"Sirui Hong, Mingchen Zhuge, Jiaqi Chen, Xiawu Zheng, Yuheng Cheng, Ceyao Zhang, Jinlin Wang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, and J\u00fcrgen Schmidhuber. 2024b. MetaGPT: Meta Programming for a Multi-Agent Collaborative Framework. In Proceedings of the 12th International Conference on Learning Representations (ICLR 2024). https:\/\/arxiv.org\/abs\/2308.00352 Published as a conference paper at ICLR 2024. Preprint available at https:\/\/arxiv.org\/abs\/2308.00352."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 13th International Conference on Learning Representations (ICLR","author":"Hu Yue","year":"2025","unstructured":"Yue Hu, Yuzhu Cai, Yaxin Du, Xinyu Zhu, Xiangrui Liu, Zijie Yu, Yuchen Hou, Shuo Tang, and Siheng Chen. 2025. Self-Evolving Multi-Agent Collaboration Networks for Software Development. In Proceedings of the 13th International Conference on Learning Representations (ICLR 2025). https:\/\/arxiv.org\/abs\/2410.16946"},{"key":"e_1_3_2_1_10_1","unstructured":"Yoichi Ishibashi and Yoshimasa Nishimura. 2024. Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization. arXiv:2404.02183 [cs.SE] https:\/\/arxiv.org\/abs\/2404.02183"},{"key":"e_1_3_2_1_11_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Lai Yuhang","year":"2023","unstructured":"Yuhang Lai, Chengxi Li, Yiming Wang, Tianyi Zhang, Ruiqi Zhong, Luke Zettlemoyer, Wen-tau Yih, Daniel Fried, Sida Wang, and Tao Yu. 2023. DS-1000: A natural and reliable benchmark for data science code generation. In International Conference on Machine Learning. PMLR, 18319-18345."},{"key":"e_1_3_2_1_12_1","unstructured":"Aodong Li Yunhan Zhao Chen Qiu Marius Kloft Padhraic Smyth Maja Rudolph and Stephan Mandt. 2024. Anomaly Detection of Tabular Data Using LLMs. arXiv:2406.16308 [cs.LG] https:\/\/arxiv.org\/abs\/2406.16308"},{"key":"e_1_3_2_1_13_1","unstructured":"Ce Li Xiaofan Liu Zhiyan Song Ce Chi Chen Zhao Jingjing Yang Zhendong Wang Kexin Yang Boshen Shi Xing Wang Chao Deng and Junlan Feng. 2025b. TReB: A Comprehensive Benchmark for Evaluating Table Reasoning Capabilities of Large Language Models. arXiv:2506.18421 [cs.CL] https:\/\/arxiv.org\/abs\/2506.18421"},{"key":"e_1_3_2_1_14_1","volume-title":"Exploration of Large Language Model Society. In Advances in Neural Information Processing Systems (NeurIPS","volume":"36","author":"Li Guohao","year":"2023","unstructured":"Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023. CAMEL: Communicative Agents for ''Mind'' Exploration of Large Language Model Society. In Advances in Neural Information Processing Systems (NeurIPS 2023), Vol. 36. Curran Associates, Inc."},{"key":"e_1_3_2_1_15_1","volume-title":"Torvik","author":"Li Lan","year":"2025","unstructured":"Lan Li, Liri Fang, Bertram Lud\u00e4scher, and Vetle I. Torvik. 2025a. AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmark. arXiv:2412.06724 [cs.DB] https:\/\/arxiv.org\/abs\/2412.06724"},{"key":"e_1_3_2_1_16_1","unstructured":"Zexi Liu Yuzhu Cai Xinyu Zhu Yujie Zheng Runkun Chen Ying Wen Yanfeng Wang Weinan E and Siheng Chen. 2025a. ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning. arXiv:2506.16499 [cs.AI] https:\/\/arxiv.org\/abs\/2506.16499"},{"key":"e_1_3_2_1_17_1","unstructured":"Zhou Liu Zhaoyang Han Guochen Yan Hao Liang Bohan Zeng Xing Chen Yuanfeng Song and Wentao Zhang. 2025b. DataGovBench: Benchmarking LLM Agents for Real-World Data Governance Workflows. arXiv:2512.04416 [cs.AI] https:\/\/arxiv.org\/abs\/2512.04416"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.gltp.2022.04.020"},{"key":"e_1_3_2_1_19_1","volume-title":"OpenRefine: an approachable open tool to clean research data","author":"Miller Meg","year":"2022","unstructured":"Meg Miller and Natalie Vielfaure. 2022. OpenRefine: an approachable open tool to clean research data. Bulletin-Association of Canadian Map Libraries and Archives (ACMLA), 170 (2022)."},{"key":"e_1_3_2_1_20_1","unstructured":"Avanika Narayan Ines Chami Laurel Orr Simran Arora and Christopher R\u00e9. 2022. Can Foundation Models Wrangle Your Data? arXiv:2205.09911 [cs.LG] https:\/\/arxiv.org\/abs\/2205.09911"},{"key":"e_1_3_2_1_21_1","unstructured":"Wei Ni Xiaoye Miao Xiangyu Zhao Yangyang Wu and Jianwei Yin. 2025. Automatic Data Repair: Are We Ready to Deploy? arXiv:2310.00711 [cs.DB] https:\/\/arxiv.org\/abs\/2310.00711"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3674399.3674436"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS). 3043-3055","author":"Park Chunjong","year":"2021","unstructured":"Chunjong Park, Anas Awadalla, Tadayoshi Kohno, and Shwetak N. Patel. 2021. Reliable and Trustworthy Machine Learning for Health Using Dataset Shift Detection. In Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS). 3043-3055. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/17e23e50bedc63b4095e3d8204ce063b-Paper.pdf"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.29379\/jedem.v13i1.625"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3054782"},{"key":"e_1_3_2_1_26_1","unstructured":"Danrui Qi Zhengjie Miao and Jiannan Wang. 2025. CleanAgent: Automating Data Standardization with LLM-based Agents. arXiv:2403.08291 [cs.LG] https:\/\/arxiv.org\/abs\/2403.08291"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Chen Qian Wei Liu Hongzhang Liu Nuo Chen Yufan Dang Jiahao Li Cheng Yang Weize Chen Yusheng Su Xin Cong Juyuan Xu Dahai Li Zhiyuan Liu and Maosong Sun. 2024. ChatDev: Communicative Agents for Software Development. arXiv:2307.07924 [cs.SE] https:\/\/arxiv.org\/abs\/2307.07924","DOI":"10.18653\/v1\/2024.acl-long.810"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.11.177"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445518"},{"key":"e_1_3_2_1_30_1","unstructured":"Zhihong Shao Peiyi Wang Qihao Zhu Runxin Xu Junxiao Song Xiao Bi Haowei Zhang Mingchuan Zhang Y. K. Li Y. Wu and Daya Guo. 2024. DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models. arXiv:2402.03300 [cs.CL] https:\/\/arxiv.org\/abs\/2402.03300"},{"key":"e_1_3_2_1_31_1","volume-title":"Tabular Data: Deep Learning is Not All You Need. arXiv:2106.03253 [cs.LG] https:\/\/arxiv.org\/abs\/2106.03253","author":"Shwartz-Ziv Ravid","year":"2021","unstructured":"Ravid Shwartz-Ziv and Amitai Armon. 2021. Tabular Data: Deep Learning is Not All You Need. arXiv:2106.03253 [cs.LG] https:\/\/arxiv.org\/abs\/2106.03253"},{"key":"e_1_3_2_1_32_1","unstructured":"Shreenidhi Srinivasan and Lydia Manikonda. 2025. Does Prompt Design Impact Quality of Data Imputation by LLMs? arXiv:2506.04172 [cs.LG] https:\/\/arxiv.org\/abs\/2506.04172"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635752"},{"key":"e_1_3_2_1_34_1","unstructured":"Xiangru Tang Yuliang Liu Zefan Cai Yanjun Shao Junjie Lu Yichi Zhang Zexuan Deng Helan Hu Kaikai An Ruijun Huang et al. 2023. ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code. arXiv preprint arXiv:2311.09835 (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the 42nd International Conference on Machine Learning (ICML 2025)","volume":"2410","author":"Trirat Patara","year":"2025","unstructured":"Patara Trirat, Wonyong Jeong, and Sung Ju Hwang. 2025. AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML. In Proceedings of the 42nd International Conference on Machine Learning (ICML 2025) (Proceedings of Machine Learning Research, Vol. 267). PMLR, to appear. https:\/\/arxiv.org\/abs\/2410.02958"},{"key":"e_1_3_2_1_36_1","volume-title":"Yiqun Hu, Sheng Zhang, Hideo Kobayashi, Jiani Zhang, Henry Zhu, Chung-Wei Hang, and Patrick Ng.","author":"Wang He","year":"2025","unstructured":"He Wang, Alexander Hanbo Li, Yiqun Hu, Sheng Zhang, Hideo Kobayashi, Jiani Zhang, Henry Zhu, Chung-Wei Hang, and Patrick Ng. 2025. DSMentor: Enhancing Data Science Agents with Curriculum Learning and Online Knowledge Accumulation. arXiv:2505.14163 [cs.AI] https:\/\/arxiv.org\/abs\/2505.14163"},{"key":"e_1_3_2_1_37_1","volume-title":"Chi, Quoc Le, and Denny Zhou","author":"Wei Jason","year":"2023","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc Le, and Denny Zhou. 2023. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. arXiv:2201.11903 [cs.CL] https:\/\/arxiv.org\/abs\/2201.11903"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34739"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1795"},{"key":"e_1_3_2_1_40_1","volume-title":"LLM-Based Agents for Tool Learning: A Survey: W. Xu et al. Data Science and Engineering","author":"Xu Weikai","year":"2025","unstructured":"Weikai Xu, Chengrui Huang, Shen Gao, and Shuo Shang. 2025. LLM-Based Agents for Tool Learning: A Survey: W. Xu et al. Data Science and Engineering (2025), 1-31."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Hongyang Yang Boyu Zhang Neng Wang Cheng Guo Xiaoli Zhang Likun Lin Junlin Wang Tianyu Zhou Mao Guan Runjia Zhang and Christina Dan Wang. 2024. FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models. arXiv:2405.14767 [q-fin.ST]","DOI":"10.2139\/ssrn.4841493"},{"key":"e_1_3_2_1_42_1","unstructured":"Shunyu Yao Jeffrey Zhao Dian Yu Nan Du Izhak Shafran Karthik Narasimhan and Yuan Cao. 2023. ReAct: Synergizing Reasoning and Acting in Language Models. arXiv:2210.03629 [cs.CL] https:\/\/arxiv.org\/abs\/2210.03629"},{"key":"e_1_3_2_1_43_1","volume-title":"Datascibench: An llm agent benchmark for data science. arXiv preprint arXiv:2502.13897","author":"Zhang Dan","year":"2025","unstructured":"Dan Zhang, Sining Zhoubian, Min Cai, Fengzu Li, Lekang Yang, Wei Wang, Tianjiao Dong, Ziniu Hu, Jie Tang, and Yisong Yue. 2025b. Datascibench: An llm agent benchmark for data science. arXiv preprint arXiv:2502.13897 (2025)."},{"key":"e_1_3_2_1_44_1","unstructured":"Lei Zhang Yuge Zhang Kan Ren Dongsheng Li and Yuqing Yang. 2024. MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks. arXiv:2304.14979 [cs.LG] https:\/\/arxiv.org\/abs\/2304.14979"},{"key":"e_1_3_2_1_45_1","unstructured":"Shaolei Zhang Ju Fan Meihao Fan Guoliang Li and Xiaoyong Du. 2025a. DeepAnalyze: Agentic Large Language Models for Autonomous Data Science. arXiv:2510.16872 [cs.AI] https:\/\/arxiv.org\/abs\/2510.16872"},{"key":"e_1_3_2_1_46_1","unstructured":"Shujian Zhang Chengyue Gong Lemeng Wu Xingchao Liu and Mingyuan Zhou. 2023. AutoML-GPT: Automatic Machine Learning with GPT. arXiv:2305.02499 [cs.CL] https:\/\/arxiv.org\/abs\/2305.02499"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-024-00266-7"},{"key":"e_1_3_2_1_48_1","unstructured":"Ruiyan Zhu Xi Cheng Ke Liu Brian Zhu Daniel Jin Neeraj Parihar Zhoutian Xu and Oliver Gao. 2025a. SheetMind: An End-to-End LLM-Powered Multi-Agent Framework for Spreadsheet Automation. arXiv:2506.12339 [cs.HC] https:\/\/arxiv.org\/abs\/2506.12339"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:17:56Z","timestamp":1786065476000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817982"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":48,"alternative-id":["10.1145\/3770855.3817982","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817982","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}