{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T21:13:49Z","timestamp":1788556429728,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":62,"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\/3770855.3817664","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:43Z","timestamp":1786036543000},"page":"5766-5777","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CoFEH: LLM-driven Feature Engineering Empowered by Collaborative Bayesian Hyperparameter Optimization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4178-2451","authenticated-orcid":false,"given":"Beicheng","family":"Xu","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\/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\/0009-0006-7840-9385","authenticated-orcid":false,"given":"Wei","family":"Liu","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\/0009-0001-0819-6445","authenticated-orcid":false,"given":"Yupeng","family":"Lu","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"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers. arXiv preprint arXiv:2503.14434","author":"Abhyankar Nikhil","year":"2025","unstructured":"Nikhil Abhyankar, Parshin Shojaee, and Chandan K Reddy. 2025. LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers. arXiv preprint arXiv:2503.14434 (2025)."},{"key":"e_1_3_2_1_2_1","first-page":"397","article-title":"Using confidence bounds for exploitation-exploration trade-offs","volume":"3","author":"Auer Peter","year":"2002","unstructured":"Peter Auer. 2002. Using confidence bounds for exploitation-exploration trade-offs. Journal of machine learning research, Vol. 3, Nov (2002), 397-422.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_3_1","volume-title":"International conference on machine learning. PMLR, 199-207","author":"Bardenet R\u00e9mi","year":"2013","unstructured":"R\u00e9mi Bardenet, M\u00e1ty\u00e1s Brendel, Bal\u00e1zs K\u00e9gl, and Michele Sebag. 2013. Collaborative hyperparameter tuning. In International conference on machine learning. PMLR, 199-207."},{"key":"e_1_3_2_1_4_1","volume-title":"Algorithms for hyper-parameter optimization. Advances in neural information processing systems","author":"Bergstra James","year":"2011","unstructured":"James Bergstra, R\u00e9mi Bardenet, Yoshua Bengio, and Bal\u00e1zs K\u00e9gl. 2011. Algorithms for hyper-parameter optimization. Advances in neural information processing systems, Vol. 24 (2011)."},{"key":"e_1_3_2_1_5_1","volume-title":"Patterns","volume":"6","author":"Bischl Bernd","year":"2025","unstructured":"Bernd Bischl, Giuseppe Casalicchio, Taniya Das, Matthias Feurer, Sebastian Fischer, Pieter Gijsbers, Subhaditya Mukherjee, Andreas C M\u00fcller, L\u00e1szl\u00f3 N\u00e9meth, Luis Oala, et al., 2025. OpenML: Insights from 10 years and more than a thousand papers. Patterns, Vol. 6, 7 (2025)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-025-5514-9"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_1_8_1","volume-title":"Bioinformatics","volume":"39","author":"Choi Hyunjun","year":"2023","unstructured":"Hyunjun Choi, Jay Moran, Nicholas Matsumoto, Miguel E Hernandez, and Jason H Moore. 2023. Aliro: an automated machine learning tool leveraging large language models. Bioinformatics, Vol. 39, 10 (2023), btad606."},{"key":"e_1_3_2_1_9_1","volume-title":"Lmpriors: Pre-trained language models as task-specific priors. arXiv preprint arXiv:2210.12530","author":"Choi Kristy","year":"2022","unstructured":"Kristy Choi, Chris Cundy, Sanjari Srivastava, and Stefano Ermon. 2022. Lmpriors: Pre-trained language models as task-specific priors. arXiv preprint arXiv:2210.12530 (2022)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/553"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679100"},{"key":"e_1_3_2_1_12_1","volume-title":"ICML AutoML Workshop.","author":"Drori Iddo","year":"2021","unstructured":"Iddo Drori, Yamuna Krishnamurthy, Remi Rampin, Raoni DE PAULA LOURENCO, Jorge Piazentin Ono, Kyunghyun Cho, Claudio Silva, and Juliana Freire. 2021. AlphaD3M: Machine Learning Pipeline Synthesis. In ICML AutoML Workshop."},{"key":"e_1_3_2_1_13_1","volume-title":"International conference on machine learning. PMLR, 1437-1446","author":"Falkner Stefan","year":"2018","unstructured":"Stefan Falkner, Aaron Klein, and Frank Hutter. 2018. BOHB: Robust and efficient hyperparameter optimization at scale. In International conference on machine learning. PMLR, 1437-1446."},{"key":"e_1_3_2_1_14_1","first-page":"1","article-title":"Auto-sklearn 2.0: Hands-free automl via meta-learning","volume":"23","author":"Feurer Matthias","year":"2022","unstructured":"Matthias Feurer, Katharina Eggensperger, Stefan Falkner, Marius Lindauer, and Frank Hutter. 2022. Auto-sklearn 2.0: Hands-free automl via meta-learning. Journal of Machine Learning Research, Vol. 23, 261 (2022), 1-61.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i16.33851"},{"key":"e_1_3_2_1_16_1","unstructured":"Google DeepMind. 2025. Gemini 2.0 Flash. https:\/\/docs.cloud.google.com\/vertex-ai\/generative-ai\/docs\/models\/gemini\/2-0-flash"},{"key":"e_1_3_2_1_17_1","volume-title":"Revisiting deep learning models for tabular data. Advances in neural information processing systems","author":"Gorishniy Yury","year":"2021","unstructured":"Yury Gorishniy, Ivan Rubachev, Valentin Khrulkov, and Artem Babenko. 2021. Revisiting deep learning models for tabular data. Advances in neural information processing systems, Vol. 34 (2021), 18932-18943."},{"key":"e_1_3_2_1_18_1","volume-title":"Why do tree-based models still outperform deep learning on typical tabular data? Advances in neural information processing systems","author":"Grinsztajn L\u00e9o","year":"2022","unstructured":"L\u00e9o Grinsztajn, Edouard Oyallon, and Ga\u00ebl Varoquaux. 2022. Why do tree-based models still outperform deep learning on typical tabular data? Advances in neural information processing systems, Vol. 35 (2022), 507-520."},{"key":"e_1_3_2_1_19_1","unstructured":"Jos\u00e9 Miguel Hern\u00e1ndez-Lobato Matthew W Hoffman and Zoubin Ghahramani. 2014. Predictive entropy search for efficient global optimization of black-box functions. In Advances in neural information processing systems. 918-926."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1938"},{"key":"e_1_3_2_1_21_1","volume-title":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 111-120","author":"Horn Franziska","year":"2019","unstructured":"Franziska Horn, Robert Pack, and Michael Rieger. 2019. The autofeat python library for automated feature engineering and selection. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 111-120."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013846"},{"key":"e_1_3_2_1_23_1","volume-title":"Exploring the true potential: Evaluating the black-box optimization capability of large language models. arXiv preprint arXiv:2404.06290","author":"Huang Beichen","year":"2024","unstructured":"Beichen Huang, Xingyu Wu, Yu Zhou, Jibin Wu, Liang Feng, Ran Cheng, and Kay Chen Tan. 2024. Exploring the true potential: Evaluating the black-box optimization capability of large language models. arXiv preprint arXiv:2404.06290 (2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25566-3_40"},{"key":"e_1_3_2_1_25_1","volume-title":"Llm-select: Feature selection with large language models. arXiv preprint arXiv:2407.02694","author":"Jeong Daniel P","year":"2024","unstructured":"Daniel P Jeong, Zachary C Lipton, and Pradeep Ravikumar. 2024. Llm-select: Feature selection with large language models. arXiv preprint arXiv:2407.02694 (2024)."},{"key":"e_1_3_2_1_26_1","volume-title":"Aide: Ai-driven exploration in the space of code. arXiv preprint arXiv:2502.13138","author":"Jiang Zhengyao","year":"2025","unstructured":"Zhengyao Jiang, Dominik Schmidt, Dhruv Srikanth, Dixing Xu, Ian Kaplan, Deniss Jacenko, and Yuxiang Wu. 2025. Aide: Ai-driven exploration in the space of code. arXiv preprint arXiv:2502.13138 (2025)."},{"key":"e_1_3_2_1_27_1","first-page":"255","volume-title":"Science","volume":"349","author":"Jordan Michael I","year":"2015","unstructured":"Michael I Jordan and Tom M Mitchell. 2015. Machine learning: Trends, perspectives, and prospects. Science, Vol. 349, 6245 (2015), 255-260."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-024-00262-x"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0123"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.31"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11678"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.237"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_29"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the AutoML Workshop at ICML","volume":"2020","author":"LeDell Erin","year":"2020","unstructured":"Erin LeDell and Sebastien Poirier. 2020. H2o automl: Scalable automatic machine learning. In Proceedings of the AutoML Workshop at ICML, Vol. 2020. 24."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-020-9971-x"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5910"},{"key":"e_1_3_2_1_37_1","volume-title":"AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions. In ICLR 2025 Worshop Emergent Possibilities and Challenges in Deep Learning for Code.","author":"Li Ziming","year":"2024","unstructured":"Ziming Li, Qianbo ZANG, David Ma, Jiawei Guo, Tuney Zheng, Minghao Liu, Xinyao Niu, Yue Wang, Jian Yang, Jiaheng Liu, et al., 2024. AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions. In ICLR 2025 Worshop Emergent Possibilities and Challenges in Deep Learning for Code."},{"key":"e_1_3_2_1_38_1","volume-title":"Large language model agent for hyper-parameter optimization. arXiv preprint arXiv:2402.01881","author":"Liu Siyi","year":"2024","unstructured":"Siyi Liu, Chen Gao, and Yong Li. 2024. Large language model agent for hyper-parameter optimization. arXiv preprint arXiv:2402.01881 (2024)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5926"},{"key":"e_1_3_2_1_40_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Liu Tennison","unstructured":"Tennison Liu, Nicol\u00e1s Astorga, Nabeel Seedat, and Mihaela van der Schaar. 2025a. Large Language Models to Enhance Bayesian Optimization. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_41_1","unstructured":"Zexi Liu Yuzhu Cai Xinyu Zhu Yujie Zheng Runkun Chen Ying Wen Yanfeng Wang Siheng Chen et al. 2025b. ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning. arXiv preprint arXiv:2506.16499 (2025)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680665"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jiixd.2024.01.002"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2932"},{"key":"e_1_3_2_1_45_1","volume-title":"Workshop on automatic machine learning. PMLR, 66-74","author":"Olson Randal S","year":"2016","unstructured":"Randal S Olson and Jason H Moore. 2016. TPOT: A tree-based pipeline optimization tool for automating machine learning. In Workshop on automatic machine learning. PMLR, 66-74."},{"key":"e_1_3_2_1_46_1","first-page":"743","article-title":"Meta-Learning by Landmarking Various Learning Algorithms","author":"Pfahringer Bernhard","year":"2000","unstructured":"Bernhard Pfahringer, Hilan Bensusan, and Christophe G Giraud-Carrier. 2000. Meta-Learning by Landmarking Various Learning Algorithms.. In ICML. 743-750.","journal-title":"ICML."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671894"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10472-011-9258-6"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0214"},{"key":"e_1_3_2_1_50_1","volume-title":"Practical bayesian optimization of machine learning algorithms. Advances in neural information processing systems","author":"Snoek Jasper","year":"2012","unstructured":"Jasper Snoek, Hugo Larochelle, and Ryan P Adams. 2012. Practical bayesian optimization of machine learning algorithms. Advances in neural information processing systems, Vol. 25 (2012)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487629"},{"key":"e_1_3_2_1_52_1","volume-title":"Lightautoml: Automl solution for a large financial services ecosystem. arXiv preprint arXiv:2109.01528","author":"Vakhrushev Anton","year":"2021","unstructured":"Anton Vakhrushev, Alexander Ryzhkov, Maxim Savchenko, Dmitry Simakov, Rinchin Damdinov, and Alexander Tuzhilin. 2021. Lightautoml: Automl solution for a large financial services ecosystem. arXiv preprint arXiv:2109.01528 (2021)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713296"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i32.39934"},{"key":"e_1_3_2_1_55_1","volume-title":"Guoyuan Zhou, Jia Guo, Hitoshi Iba, and Kenji Tei.","author":"Xu Jinglue","year":"2024","unstructured":"Jinglue Xu, Jialong Li, Zhen Liu, Nagar Anthel Venkatesh Suryanarayanan, Guoyuan Zhou, Jia Guo, Hitoshi Iba, and Kenji Tei. 2024. Large language models synergize with automated machine learning. arXiv preprint arXiv:2405.03727 (2024)."},{"key":"e_1_3_2_1_56_1","volume-title":"Taking human out of learning applications: A survey on automated machine learning. arXiv preprint arXiv:1810.13306","author":"Yao Quanming","year":"2018","unstructured":"Quanming Yao, Mengshuo Wang, Yuqiang Chen, Wenyuan Dai, Yu-Feng Li, Wei-Wei Tu, Qiang Yang, and Yang Yu. 2018. Taking human out of learning applications: A survey on automated machine learning. arXiv preprint arXiv:1810.13306, Vol. 31 (2018)."},{"key":"e_1_3_2_1_57_1","volume-title":"Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems, Vol. 36 (2023), 11809-11822."},{"key":"e_1_3_2_1_58_1","first-page":"1077","article-title":"Efficient transfer learning method for automatic hyperparameter tuning. In Artificial intelligence and statistics","author":"Yogatama Dani","year":"2014","unstructured":"Dani Yogatama and Gideon Mann. 2014. Efficient transfer learning method for automatic hyperparameter tuning. In Artificial intelligence and statistics. PMLR, 1077-1085.","journal-title":"PMLR"},{"key":"e_1_3_2_1_59_1","volume-title":"Automl-gpt: Automatic machine learning with gpt. arXiv preprint arXiv:2305.02499","author":"Zhang Shujian","year":"2023","unstructured":"Shujian Zhang, Chengyue Gong, Lemeng Wu, Xingchao Liu, and Mingyuan Zhou. 2023a. Automl-gpt: Automatic machine learning with gpt. arXiv preprint arXiv:2305.02499 (2023)."},{"key":"e_1_3_2_1_60_1","volume-title":"International Conference on Machine Learning. PMLR, 41880-41901","author":"Zhang Tianping","year":"2023","unstructured":"Tianping Zhang, Zheyu Aqa Zhang, Zhiyuan Fan, Haoyan Luo, Fengyuan Liu, Qian Liu, Wei Cao, and Li Jian. 2023b. Openfe: Automated feature generation with expert-level performance. In International Conference on Machine Learning. PMLR, 41880-41901."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/782"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-024-00264-9"}],"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":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770855.3817664","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T20:34:17Z","timestamp":1788554057000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817664"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":62,"alternative-id":["10.1145\/3770855.3817664","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817664","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"}}]}}