{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T02:03:31Z","timestamp":1780020211979,"version":"3.53.1"},"reference-count":57,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100007224","name":"National Foundation for Science and Technology Development","doi-asserted-by":"publisher","award":["102.03-2023.14"],"award-info":[{"award-number":["102.03-2023.14"]}],"id":[{"id":"10.13039\/100007224","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Future Generation Computer Systems"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.future.2026.108510","type":"journal-article","created":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T15:11:35Z","timestamp":1775315495000},"page":"108510","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A program-centered approach to solving AI tasks with ready-to-use models"],"prefix":"10.1016","volume":"182","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3144-743X","authenticated-orcid":false,"given":"Tung-Thuy","family":"Pham","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2267-2592","authenticated-orcid":false,"given":"Minh-Quan","family":"Duong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1613-9872","authenticated-orcid":false,"given":"Duy-Quan","family":"Luong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1926-8202","authenticated-orcid":false,"given":"Trung-Hieu","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3596-2352","authenticated-orcid":false,"given":"Thu-Trang","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8970-9870","authenticated-orcid":false,"given":"Son","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9407-1971","authenticated-orcid":false,"given":"Hieu Dinh","family":"Vo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.future.2026.108510_b1","article-title":"Deep learning for computer vision: A brief review","volume":"2018","author":"Voulodimos","year":"2018","journal-title":"Comput. Intell. Neurosci."},{"key":"10.1016\/j.future.2026.108510_b2","series-title":"Generating critical scenarios for testing automated driving systems","author":"Nguyen","year":"2024"},{"issue":"6","key":"10.1016\/j.future.2026.108510_b3","doi-asserted-by":"crossref","first-page":"1236","DOI":"10.1093\/bib\/bbx044","article-title":"Deep learning for healthcare: review, opportunities and challenges","volume":"19","author":"Miotto","year":"2018","journal-title":"Brief. Bioinform."},{"key":"10.1016\/j.future.2026.108510_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2020.106384","article-title":"Deep learning for financial applications: A survey","volume":"93","author":"Ozbayoglu","year":"2020","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.future.2026.108510_b5","series-title":"2019 34th IEEE\/ACM International Conference on Automated Software Engineering Workshop","first-page":"126","article-title":"On the engineering of AI-powered systems","author":"Kusmenko","year":"2019"},{"key":"10.1016\/j.future.2026.108510_b6","doi-asserted-by":"crossref","unstructured":"C. K\u00e4stner, E. Kang, Teaching software engineering for AI-enabled systems, in: Proceedings of the ACM\/IEEE 42nd International Conference on Software Engineering: Software Engineering Education and Training, 2020, pp. 45\u201348.","DOI":"10.1145\/3377814.3381714"},{"key":"10.1016\/j.future.2026.108510_b7","doi-asserted-by":"crossref","first-page":"0063","DOI":"10.34133\/icomputing.0063","article-title":"Taskmatrix. ai: Completing tasks by connecting foundation models with millions of apis","volume":"3","author":"Liang","year":"2024","journal-title":"Intell. Comput."},{"key":"10.1016\/j.future.2026.108510_b8","series-title":"The computational limits of deep learning","author":"Thompson","year":"2022"},{"key":"10.1016\/j.future.2026.108510_b9","first-page":"38154","article-title":"Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face","volume":"36","author":"Shen","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.future.2026.108510_b10","first-page":"4540","article-title":"Taskbench: Benchmarking large language models for task automation","volume":"37","author":"Shen","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.future.2026.108510_b11","series-title":"CABENCH: Benchmarking composable AI for solving complex tasks through composing ready-to-use models","author":"Pham","year":"2025"},{"key":"10.1016\/j.future.2026.108510_b12","series-title":"Mle-bench: Evaluating machine learning agents on machine learning engineering","author":"Chan","year":"2024"},{"key":"10.1016\/j.future.2026.108510_b13","unstructured":"S. Hong, M. Zhuge, J. Chen, X. Zheng, Y. Cheng, C. Zhang, J. Wang, Z. Wang, S.K.S. Yau, Z. Lin, et al., METAGPT: META PROGRAMMING FOR A MULTI-AGENT COLLABORATIVE FRAMEWORK, in: 12th International Conference on Learning Representations, ICLR 2024, 2024."},{"key":"10.1016\/j.future.2026.108510_b14","series-title":"Aflow: Automating agentic workflow generation","author":"Zhang","year":"2024"},{"key":"10.1016\/j.future.2026.108510_b15","doi-asserted-by":"crossref","unstructured":"M.A. Islam, M.E. Ali, M.R. Parvez, MapCoder: Multi-Agent Code Generation for Competitive Problem Solving, in: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024, pp. 4912\u20134944.","DOI":"10.18653\/v1\/2024.acl-long.269"},{"key":"10.1016\/j.future.2026.108510_b16","series-title":"Paper2code: Automating code generation from scientific papers in machine learning","author":"Seo","year":"2025"},{"key":"10.1016\/j.future.2026.108510_b17","doi-asserted-by":"crossref","unstructured":"J. Devlin, M.-W. Chang, K. Lee, K. Toutanova, Bert: Pre-training of deep bidirectional transformers for language understanding, in: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 2019, pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.1016\/j.future.2026.108510_b18","series-title":"ReAct: Synergizing reasoning and acting in language models","author":"Yao","year":"2023"},{"key":"10.1016\/j.future.2026.108510_b19","series-title":"Automated design of agentic systems","author":"Hu","year":"2024"},{"key":"10.1016\/j.future.2026.108510_b20","series-title":"Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks","author":"Chen","year":"2022"},{"key":"10.1016\/j.future.2026.108510_b21","series-title":"A Program-Centered Approach to Solving AI Tasks with Ready-to-Use Models","author":"Anonymous","year":"2025"},{"key":"10.1016\/j.future.2026.108510_b22","series-title":"Applied Statistics and Probability for Engineers","author":"Montgomery","year":"2010"},{"key":"10.1016\/j.future.2026.108510_b23","unstructured":"K. Stechly, K. Valmeekam, S. Kambhampati, Chain of thoughtlessness? an analysis of cot in planning, in: The Thirty-Eighth Annual Conference on Neural Information Processing Systems, 2024."},{"key":"10.1016\/j.future.2026.108510_b24","first-page":"68539","article-title":"Toolformer: Language models can teach themselves to use tools","volume":"36","author":"Schick","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.future.2026.108510_b25","first-page":"126544","article-title":"Gorilla: Large language model connected with massive apis","volume":"37","author":"Patil","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"10","key":"10.1016\/j.future.2026.108510_b26","first-page":"1","article-title":"Foundations & trends in multimodal machine learning: Principles, challenges, and open questions","volume":"56","author":"Liang","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.future.2026.108510_b27","first-page":"17","article-title":"Challenges and applications in multimodal machine learning","author":"Baltru\u0161aitis","year":"2018","journal-title":"Handb. Multimodal-Multisensor Interfaces: Signal Process. Archit. Detect. Emot. Cognition-Volume 2"},{"key":"10.1016\/j.future.2026.108510_b28","series-title":"CABENCH: Benchmarking Composable AI for Solving Complex Tasks through Composing Ready-to-Use Models","author":"Pham","year":"2025"},{"key":"10.1016\/j.future.2026.108510_b29","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.future.2026.108510_b30","series-title":"Self-consistency improves chain of thought reasoning in language models","author":"Wang","year":"2022"},{"key":"10.1016\/j.future.2026.108510_b31","first-page":"46534","article-title":"Self-refine: Iterative refinement with self-feedback","volume":"36","author":"Madaan","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.future.2026.108510_b32","series-title":"Expertprompting: Instructing large language models to be distinguished experts","author":"Xu","year":"2023"},{"key":"10.1016\/j.future.2026.108510_b33","series-title":"Take a step back: Evoking reasoning via abstraction in large language models","author":"Zheng","year":"2023"},{"key":"10.1016\/j.future.2026.108510_b34","series-title":"MAS-ZERO: Designing multi-agent systems with zero supervision","author":"Ke","year":"2025"},{"key":"10.1016\/j.future.2026.108510_b35","series-title":"Mdocagent: A multi-modal multi-agent framework for document understanding","author":"Han","year":"2025"},{"key":"10.1016\/j.future.2026.108510_b36","series-title":"MAS-GPT: Training LLMs to build LLM-based multi-agent systems","author":"Ye","year":"2025"},{"key":"10.1016\/j.future.2026.108510_b37","doi-asserted-by":"crossref","unstructured":"Y. Wang, W. Wang, S. Joty, S.C. Hoi, CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation, in: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021, pp. 8696\u20138708.","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"10.1016\/j.future.2026.108510_b38","doi-asserted-by":"crossref","unstructured":"D. Guo, S. Lu, N. Duan, Y. Wang, M. Zhou, J. Yin, UniXcoder: Unified Cross-Modal Pre-training for Code Representation, in: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022, pp. 7212\u20137225.","DOI":"10.18653\/v1\/2022.acl-long.499"},{"key":"10.1016\/j.future.2026.108510_b39","series-title":"Codegen: An open large language model for code with multi-turn program synthesis","author":"Nijkamp","year":"2022"},{"key":"10.1016\/j.future.2026.108510_b40","series-title":"Wizardcoder: Empowering code large language models with evol-instruct","author":"Luo","year":"2023"},{"key":"10.1016\/j.future.2026.108510_b41","doi-asserted-by":"crossref","unstructured":"Q. Zheng, X. Xia, X. Zou, Y. Dong, S. Wang, Y. Xue, L. Shen, Z. Wang, A. Wang, Y. Li, et al., Codegeex: A pre-trained model for code generation with multilingual benchmarking on humaneval-x, in: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023, pp. 5673\u20135684.","DOI":"10.1145\/3580305.3599790"},{"key":"10.1016\/j.future.2026.108510_b42","series-title":"Starcoder: may the source be with you!","author":"Li","year":"2023"},{"key":"10.1016\/j.future.2026.108510_b43","series-title":"Code llama: Open foundation models for code","author":"Roziere","year":"2023"},{"key":"10.1016\/j.future.2026.108510_b44","doi-asserted-by":"crossref","DOI":"10.1016\/j.jss.2023.111786","article-title":"Arist: An effective api argument recommendation approach","volume":"204","author":"Nguyen","year":"2023","journal-title":"J. Syst. Softw."},{"key":"10.1016\/j.future.2026.108510_b45","series-title":"2019 34th IEEE\/ACM International Conference on Automated Software Engineering","first-page":"710","article-title":"Combining program analysis and statistical language model for code statement completion","author":"Nguyen","year":"2019"},{"key":"10.1016\/j.future.2026.108510_b46","series-title":"Codet: Code generation with generated tests","author":"Chen","year":"2022"},{"key":"10.1016\/j.future.2026.108510_b47","series-title":"Rambo: Enhancing rag-based repository-level method body completion","author":"Bui","year":"2024"},{"key":"10.1016\/j.future.2026.108510_b48","doi-asserted-by":"crossref","unstructured":"F. Zhang, B. Chen, Y. Zhang, J. Keung, J. Liu, D. Zan, Y. Mao, J.-G. Lou, W. Chen, RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation, in: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023, pp. 2471\u20132484.","DOI":"10.18653\/v1\/2023.emnlp-main.151"},{"key":"10.1016\/j.future.2026.108510_b49","doi-asserted-by":"crossref","unstructured":"X. Wang, Y. Wang, Y. Wan, F. Mi, Y. Li, P. Zhou, J. Liu, H. Wu, X. Jiang, Q. Liu, Compilable Neural Code Generation with Compiler Feedback, in: Findings of the Association for Computational Linguistics: ACL 2022, 2022, pp. 9\u201319.","DOI":"10.18653\/v1\/2022.findings-acl.2"},{"key":"10.1016\/j.future.2026.108510_b50","series-title":"A closer look at conditional prompt tuning for vision-language models","author":"Zhang","year":"2025"},{"key":"10.1016\/j.future.2026.108510_b51","doi-asserted-by":"crossref","unstructured":"C. Wang, Y. Yang, C. Gao, Y. Peng, H. Zhang, M.R. Lyu, No more fine-tuning? an experimental evaluation of prompt tuning in code intelligence, in: Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2022, pp. 382\u2013394.","DOI":"10.1145\/3540250.3549113"},{"key":"10.1016\/j.future.2026.108510_b52","series-title":"2025 IEEE\/ACM 22nd International Conference on Mining Software Repositories","first-page":"490","article-title":"Prompt engineering or fine-tuning: An empirical assessment of llms for code","author":"Shin","year":"2025"},{"key":"10.1016\/j.future.2026.108510_b53","article-title":"Efficient and robust automated machine learning","volume":"28","author":"Feurer","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.future.2026.108510_b54","series-title":"Workshop on Automatic Machine Learning","first-page":"66","article-title":"TPOT: A tree-based pipeline optimization tool for automating machine learning","author":"Olson","year":"2016"},{"key":"10.1016\/j.future.2026.108510_b55","first-page":"24","article-title":"H2o automl: Scalable automatic machine learning","volume":"vol. 2020","author":"LeDell","year":"2020"},{"key":"10.1016\/j.future.2026.108510_b56","series-title":"International Conference on Machine Learning","first-page":"8007","article-title":"Automl-zero: Evolving machine learning algorithms from scratch","author":"Real","year":"2020"},{"key":"10.1016\/j.future.2026.108510_b57","doi-asserted-by":"crossref","unstructured":"B. Zoph, V. Vasudevan, J. Shlens, Q.V. Le, Learning transferable architectures for scalable image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8697\u20138710.","DOI":"10.1109\/CVPR.2018.00907"}],"container-title":["Future Generation Computer Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167739X26001445?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167739X26001445?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T01:38:09Z","timestamp":1780018689000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167739X26001445"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":57,"alternative-id":["S0167739X26001445"],"URL":"https:\/\/doi.org\/10.1016\/j.future.2026.108510","relation":{},"ISSN":["0167-739X"],"issn-type":[{"value":"0167-739X","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A program-centered approach to solving AI tasks with ready-to-use models","name":"articletitle","label":"Article Title"},{"value":"Future Generation Computer Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.future.2026.108510","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108510"}}