{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T10:06:20Z","timestamp":1778925980185,"version":"3.51.4"},"reference-count":24,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T00:00:00Z","timestamp":1774224000000},"content-version":"vor","delay-in-days":81,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LR22F020005"],"award-info":[{"award-number":["LR22F020005"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["AI Open"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1016\/j.aiopen.2026.03.001","type":"journal-article","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T07:09:30Z","timestamp":1775027370000},"page":"133-141","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Who is the most suitable one? Compliance review method based on multi-agent routing"],"prefix":"10.1016","volume":"7","author":[{"given":"Chutian","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangqian","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0169-4831","authenticated-orcid":false,"given":"Xin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meijin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lijun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjie","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5574-9682","authenticated-orcid":false,"given":"Dezheng","family":"Bao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5058-4417","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.aiopen.2026.03.001_b1","article-title":"The promise of automated compliance checking","volume":"5","author":"Amor","year":"2021","journal-title":"Dev. Built Environ."},{"key":"10.1016\/j.aiopen.2026.03.001_b2","unstructured":"Brown, T.B., et al., 2020. Language Models are Few-Shot Learners. In: NeurIPS. arXiv preprint, arXiv:2005.14165."},{"key":"10.1016\/j.aiopen.2026.03.001_b3","doi-asserted-by":"crossref","unstructured":"Chen, J., Saha, S., Bansal, M., 2024. ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). pp. 7066\u20137085.","DOI":"10.18653\/v1\/2024.acl-long.381"},{"key":"10.1016\/j.aiopen.2026.03.001_b4","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K., 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In: NAACL."},{"key":"10.1016\/j.aiopen.2026.03.001_b5","unstructured":"Du, Y., Li, S., Torralba, A., Tenenbaum, J.B., Mordatch, I., 2023. Improving factuality and reasoning in language models through multiagent debate. In: Forty-First International Conference on Machine Learning. arXiv preprint, arXiv:2305.14325."},{"key":"10.1016\/j.aiopen.2026.03.001_b6","doi-asserted-by":"crossref","unstructured":"Liang, T., He, Z., Jiao, W., Wang, X., Wang, Y., Wang, R., Yang, Y., Shi, S., Tu, Z., 2024. Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. pp. 17889\u201317904.","DOI":"10.18653\/v1\/2024.emnlp-main.992"},{"key":"10.1016\/j.aiopen.2026.03.001_b7","doi-asserted-by":"crossref","unstructured":"Luo, C., Shen, Y., Zhu, Z., Zheng, Q., Yu, Z., Yao, C., 2024. Layoutllm: Layout instruction tuning with large language models for document understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 15630\u201315640.","DOI":"10.1109\/CVPR52733.2024.01480"},{"key":"10.1016\/j.aiopen.2026.03.001_b8","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.aiopen.2026.03.001_b9","unstructured":"Mikolov, T., et al., 2013. Efficient Estimation of Word Representations in Vector Space. In: ICLR. arXiv preprint: arXiv:1301.3781."},{"key":"10.1016\/j.aiopen.2026.03.001_b10","series-title":"Large language models: A survey","author":"Minaee","year":"2024"},{"key":"10.1016\/j.aiopen.2026.03.001_b11","series-title":"GPT-4 technical report","author":"OpenAI","year":"2023"},{"issue":"1","key":"10.1016\/j.aiopen.2026.03.001_b12","doi-asserted-by":"crossref","first-page":"7065","DOI":"10.1038\/s41598-023-34342-1","article-title":"Automated code compliance checking research based on BIM and knowledge graph","volume":"13","author":"Peng","year":"2023","journal-title":"Sci. Rep."},{"key":"10.1016\/j.aiopen.2026.03.001_b13","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I., 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In: EMNLP.","DOI":"10.18653\/v1\/D19-1410"},{"key":"10.1016\/j.aiopen.2026.03.001_b14","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/j.autcon.2015.03.003","article-title":"Classification of rules for automated BIM rule checking development","volume":"53","author":"Solihin","year":"2015","journal-title":"Autom. Constr."},{"key":"10.1016\/j.aiopen.2026.03.001_b15","article-title":"State grid corporation of China 2024 annual report","author":"State Grid Corporation of China","year":"2024","journal-title":"SGCC Rep."},{"key":"10.1016\/j.aiopen.2026.03.001_b16","series-title":"LLaMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"10.1016\/j.aiopen.2026.03.001_b17","doi-asserted-by":"crossref","unstructured":"Wang, S., Huang, L., 2024. Debate as Optimization: Adaptive Conformal Prediction and Diverse Retrieval for Event Extraction. In: Findings of the Association for Computational Linguistics: EMNLP 2024. pp. 16422\u201316435.","DOI":"10.18653\/v1\/2024.findings-emnlp.958"},{"key":"10.1016\/j.aiopen.2026.03.001_b18","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.aiopen.2026.03.001_b19","doi-asserted-by":"crossref","unstructured":"Xiong, K., Ding, X., Cao, Y., Liu, T., Qin, B., 2023. Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate. In: The 2023 Conference on Empirical Methods in Natural Language Processing.","DOI":"10.18653\/v1\/2023.findings-emnlp.508"},{"key":"10.1016\/j.aiopen.2026.03.001_b20","first-page":"11809","article-title":"Tree of thoughts: Deliberate problem solving with large language models","volume":"36","author":"Yao","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"2","key":"10.1016\/j.aiopen.2026.03.001_b21","doi-asserted-by":"crossref","DOI":"10.1061\/(ASCE)CP.1943-5487.0000346","article-title":"Semantic NLP-based information extraction from construction regulatory documents for automated compliance checking","volume":"30","author":"Zhang","year":"2016","journal-title":"J. Comput. Civ. Eng."},{"key":"10.1016\/j.aiopen.2026.03.001_b22","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.autcon.2016.08.027","article-title":"Integrating semantic NLP and logic reasoning into a unified system for fully-automated code checking","volume":"73","author":"Zhang","year":"2017","journal-title":"Autom. Constr."},{"key":"10.1016\/j.aiopen.2026.03.001_b23","series-title":"A survey of large language models","author":"Zhao","year":"2023"},{"key":"10.1016\/j.aiopen.2026.03.001_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2020.101195","article-title":"A building regulation question answering system: A deep learning methodology","volume":"46","author":"Zhong","year":"2020","journal-title":"Adv. Eng. Inform."}],"container-title":["AI Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666651026000082?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666651026000082?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T09:06:25Z","timestamp":1778922385000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2666651026000082"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":24,"alternative-id":["S2666651026000082"],"URL":"https:\/\/doi.org\/10.1016\/j.aiopen.2026.03.001","relation":{},"ISSN":["2666-6510"],"issn-type":[{"value":"2666-6510","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Who is the most suitable one? Compliance review method based on multi-agent routing","name":"articletitle","label":"Article Title"},{"value":"AI Open","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.aiopen.2026.03.001","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Publishing services by Elsevier B.V. on behalf of KeAi Communications Co. Ltd.","name":"copyright","label":"Copyright"}]}}