{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T16:09:29Z","timestamp":1774541369489,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3673923","type":"journal-article","created":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T19:54:46Z","timestamp":1773431686000},"page":"41932-41945","source":"Crossref","is-referenced-by-count":1,"title":["AutoML-Pipeline: A RAG-Enhanced Code Generation Framework With Pre-Validation for Cloud-Native Machine Learning Workflows"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1510-8477","authenticated-orcid":false,"given":"Wenyu","family":"Zhao","sequence":"first","affiliation":[{"name":"Microsoft, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4963-9402","authenticated-orcid":false,"given":"Tingjie","family":"Chen","sequence":"additional","affiliation":[{"name":"Intel, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9826-4252","authenticated-orcid":false,"given":"Jie Si","family":"Yang","sequence":"additional","affiliation":[{"name":"The University of Utah, Salt Lake City, UT, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2879-5327","authenticated-orcid":false,"given":"Lei","family":"Qiu","sequence":"additional","affiliation":[{"name":"Ningbo University of Technology, Ningbo, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IMCEC55388.2022.10020005"},{"issue":"4","key":"ref2","first-page":"39","article-title":"Accelerating the machine learning lifecycle with MLflow","volume":"41","author":"Zaharia","year":"2018","journal-title":"IEEE Data Eng. Bull."},{"key":"ref3","volume-title":"Azure Machine Learning Documentation","year":"2021"},{"key":"ref4","volume-title":"Amazon Sagemaker Developer Guide","year":"2021"},{"key":"ref5","volume-title":"Vertex AI Documentation","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.14778\/3297753.3297763"},{"key":"ref7","first-page":"1","article-title":"MLlib: Machine learning in apache spark","author":"Meng","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3054782"},{"key":"ref9","first-page":"2503","article-title":"Hidden technical debt in machine learning systems","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Sculley"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00068"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380395"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3533378"},{"key":"ref13","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref14","article-title":"Code llama: Open foundation models for code","author":"Rozi\u00e8re","year":"2023","journal-title":"arXiv:2308.12950"},{"key":"ref15","article-title":"StarCoder: May the source be with you!","author":"Li","year":"2023","journal-title":"arXiv:2305.06161"},{"key":"ref16","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021","journal-title":"arXiv:2107.03374"},{"key":"ref17","article-title":"Program synthesis with large language models","author":"Austin","year":"2021","journal-title":"arXiv:2108.07732"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3520312.3534862"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3773"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3695988"},{"key":"ref21","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Lewis"},{"key":"ref22","article-title":"Retrieval-augmented generation for large language models: A survey","author":"Gao","year":"2023","journal-title":"arXiv:2312.10997"},{"key":"ref23","first-page":"2206","article-title":"Improving language models by retrieving from trillions of tokens","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Borgeaud"},{"issue":"251","key":"ref24","first-page":"1","article-title":"Atlas: Few-shot learning with retrieval augmented language models","volume":"24","author":"Izacard","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.232"},{"key":"ref26","article-title":"DocPrompting: Generating code by retrieving the docs","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Zhou"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1057"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1041"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"ref30","article-title":"GraphCodeBERT: Pre-training code representations with data flow","author":"Guo","year":"2020","journal-title":"arXiv:2009.08366"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1126\/science.abq1158"},{"key":"ref32","article-title":"CodeGen: An open large language model for code with multi-turn program synthesis","author":"Nijkamp","year":"2022","journal-title":"arXiv:2203.13474"},{"key":"ref33","article-title":"InCoder: A generative model for code infilling and synthesis","author":"Fried","year":"2022","journal-title":"arXiv:2204.05999"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.68"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510203"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3689735"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00205"},{"key":"ref38","first-page":"31693","article-title":"Repository-level prompt generation for large language models of code","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shrivastava"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"ref40","article-title":"Self-rag: Learning to retrieve, generate, and critique through self-reflection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Asai"},{"key":"ref41","first-page":"27670","article-title":"Baleen: Robust multi-hop reasoning at scale via condensed retrieval","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Khattab"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.431"},{"key":"ref43","first-page":"21314","article-title":"CodeRL: Mastering code generation through pretrained models and deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Le"},{"key":"ref44","article-title":"CodeT: Code generation with generated tests","author":"Chen","year":"2022","journal-title":"arXiv:2207.10397"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.442"},{"key":"ref46","article-title":"CodeXGLUE: A machine learning benchmark dataset for code understanding and generation","author":"Lu","year":"2021","journal-title":"arXiv:2102.04664"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098021"},{"key":"ref48","volume-title":"Kubeflow: Machine Learning Toolkit for Kubernetes","year":"2018"},{"key":"ref49","volume-title":"Metaflow: A Framework for Real-life Data Science","year":"2019"},{"key":"ref50","volume-title":"ZenML: An Extensible Open-source MLOPS Framework","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_3"},{"key":"ref52","article-title":"Hyperparameter optimization: A spectral approach","author":"Hazan","year":"2017","journal-title":"arXiv:1706.00764"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA.2015.7344858"},{"key":"ref54","first-page":"33","article-title":"Plumber: Diagnosing and removing performance bottlenecks in machine learning data pipelines","volume-title":"Proc. Mach. Learn. Syst.","volume":"4","author":"Kuchnik"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3360594"},{"key":"ref56","volume-title":"Amazon Sagemaker Autopilot","year":"2021"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.14778\/3430915.3430917"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3452759"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.14778\/3229863.3229867"},{"key":"ref60","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11433654.pdf?arnumber=11433654","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T19:57:33Z","timestamp":1774468653000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11433654\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3673923","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}