{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T15:09:10Z","timestamp":1774883350447,"version":"3.50.1"},"reference-count":51,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T00:00:00Z","timestamp":1773187200000},"content-version":"vor","delay-in-days":11,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52568010"],"award-info":[{"award-number":["52568010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,2,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Building fires are pervasive, high-consequence events, yet current inspection workflows remain inefficient. We propose a cognitively guided hybrid-optimization method that operationalizes modular prompt engineering for open-source visual-language models (VLMs) to automate building fire-hazard identification. Grounded in the ACT-R (adaptive control of thought-rational) architecture, the approach decomposes professional reasoning into five optimizable modules and searches the discrete prompt space via a two-stage Bayesian-genetic procedure. Evaluated on 612 images spanning four hazard categories\u2014structural damage, evacuation route, fire equipment missing, and debris accumulation\u2014the system achieves 90.75% macro-F1 with 94.96% recall, outperforming Low-Rank Adaptation (LoRA) fine-tuning (86.35% macro-F1 with 100 training images) using zero training data, while matching proprietary models and retaining the flexibility of open-source VLMs. The results show that methodical prompt modularization and hybrid optimization can elicit professional-level performance in safety-critical tasks without model retraining, providing a scalable and practical computational pipeline for Artificial Intelligence (AI) assisted urban building safety supervision.<\/jats:p>","DOI":"10.1093\/jcde\/qwag022","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T12:39:16Z","timestamp":1773146356000},"page":"305-330","source":"Crossref","is-referenced-by-count":0,"title":["Cognitively guided hybrid optimization method for visual-language models in building fire-risk identification"],"prefix":"10.1093","volume":"13","author":[{"given":"Di","family":"Zhang","sequence":"first","affiliation":[{"name":"Cornell University Department of City and Regional Planning, , Ithaca, New York 14853 ,","place":["USA"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xu","sequence":"additional","affiliation":[{"name":"Architecture and Design College, Nanchang University , No. 999, Xuefu Avenue, Honggutan New District, Nanchang 330031 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6330-6723","authenticated-orcid":false,"given":"Jiaxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Architecture and Design College, Nanchang University , No. 999, Xuefu Avenue, Honggutan New District, Nanchang 330031 ,","place":["China"]},{"name":"Division of Sustainable Energy and Environmental Engineering, Graduate School of Engineering, Osaka University , Suita, Osaka 565-0871 ,","place":["Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2026,3,11]]},"reference":[{"key":"2026033010380563100_bib4","doi-asserted-by":"publisher","first-page":"13290","DOI":"10.48084\/etasr.6753","article-title":"Real-time inspection of fire safety equipment using computer vision and deep learning","volume":"14","author":"Alayed","year":"2024","journal-title":"Engineering, Technology and Applied Science Research"},{"key":"2026033010380563100_bib5","doi-asserted-by":"publisher","first-page":"1036","DOI":"10.1037\/0033-295X.111.4.1036","article-title":"An integrated theory of the mind","volume":"111","author":"Anderson","year":"2004","journal-title":"Psychological Review"},{"key":"2026033010380563100_bib6","doi-asserted-by":"publisher","first-page":"Article 9095","DOI":"10.3390\/s23229095","article-title":"Deep learning based fire risk detection on construction sites","volume":"23","author":"Ann","year":"2023","journal-title":"Sensors (Basel, Switzerland)"},{"key":"2026033010380563100_bib7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.13923","volume-title":"Qwen2.5-VL Technical Report","author":"Bai","year":"2025"},{"key":"2026033010380563100_bib8","volume-title":"World Health Organization.","author":"Burns","year":"2023"},{"key":"2026033010380563100_bib9","doi-asserted-by":"publisher","first-page":"Article 102614","DOI":"10.1016\/j.aei.2024.102614","article-title":"Automated fire risk assessment and mitigation in building blueprints using computer vision and deep generative models","volume":"62","author":"Chen","year":"2024","journal-title":"Advanced Engineering Informatics"},{"key":"2026033010380563100_bib10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.autcon.2018.11.020","article-title":"Optimal path planning in real time for dynamic building fire rescue operations using wireless sensors and visual guidance","volume":"99","author":"Chou","year":"2019","journal-title":"Automation in Construction"},{"key":"2026033010380563100_bib11","doi-asserted-by":"publisher","first-page":"Article 103623","DOI":"10.1016\/j.inffus.2025.103623","article-title":"A comprehensive survey of vision\u2013language models: pretrained models, fine-tuning, prompt engineering, adapters, and benchmark datasets","volume":"126","author":"Danish","year":"2026","journal-title":"Information Fusion"},{"key":"2026033010380563100_bib1","doi-asserted-by":"crossref","DOI":"10.18356\/9789210015059","article-title":"Global Assessment Report on Disaster Risk Reduction 2022: Our World at Risk: Transforming Governance for a Resilient Future","author":"United Nations Office for Disaster Risk Reduction (UNDRR).","year":"2022"},{"key":"2026033010380563100_bib12","doi-asserted-by":"publisher","first-page":"Article 3191","DOI":"10.1109\/JSEN.2019.2894665","article-title":"Fire sensing technologies: a review","volume":"19","author":"Gaur","year":"2019","journal-title":"IEEE Sensors Journal"},{"key":"2026033010380563100_bib13","volume-title":"Code for Fire Protection Design of Buildings","author":"Ministry of Housing and Urban-Rural Development of the People\u2019s Republic of China","year":"2014"},{"key":"2026033010380563100_bib3","volume-title":"GPT-4V(Ision) System Card","author":"OpenAI","year":"2023"},{"key":"2026033010380563100_bib14","article-title":"Connecting large language models with evolutionary algorithms yields powerful prompt optimizers","author":"Guo","year":"2023"},{"key":"2026033010380563100_bib15","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1080\/15326900701326402","article-title":"Typicality, graded membership, and vagueness","volume":"31","author":"Hampton","year":"2007","journal-title":"Cognitive Science"},{"key":"2026033010380563100_bib2","volume-title":"Existing Building Safety \u2013 A Guideline for Inspection","author":"World Organization of Building Officials (WOBO)","year":"2023"},{"key":"2026033010380563100_bib16","doi-asserted-by":"publisher","first-page":"Article 315","DOI":"10.3390\/fire6080315","article-title":"Video fire detection methods based on deep learning: datasets, methods, and future directions","volume":"6","author":"Jin","year":"2023","journal-title":"Fire"},{"key":"2026033010380563100_bib17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.eswa.2021.115125","article-title":"DeepSmoke: deep learning model for smoke detection and segmentation in outdoor environments","volume":"182","author":"Khan","year":"2021","journal-title":"Expert Systems with Applications"},{"key":"2026033010380563100_bib18","doi-asserted-by":"publisher","first-page":"19113","DOI":"10.1109\/CVPR52729.2023.01832","article-title":"MaPLe: multi-modal prompt learning","author":"Khattak","year":"2023"},{"key":"2026033010380563100_bib19","volume-title":"LLaVA-NeXT: stronger llms supercharge multimodal capabilities in the wild","author":"Li","year":"2024"},{"key":"2026033010380563100_bib20","first-page":"202","volume-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"2026033010380563100_bib21","doi-asserted-by":"publisher","first-page":"100625","DOI":"10.1016\/j.csite.2020.100625","article-title":"Image fire detection algorithms based on convolutional neural networks","volume":"19","author":"Li","year":"2020","journal-title":"Case Studies in Thermal Engineering"},{"key":"2026033010380563100_bib22","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"2026033010380563100_bib23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3560815","article-title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","author":"Liu","year":"2023"},{"key":"2026033010380563100_bib24","article-title":"Building safety inspection: Everything you need to know","author":"Lopez","year":"2023","journal-title":"Eastern Engineering Group"},{"key":"2026033010380563100_bib25","doi-asserted-by":"publisher","first-page":"1663","DOI":"10.1177\/0956797614541991","article-title":"Utilizing\u201d signal detection theory","volume":"25","author":"Lynn","year":"2014","journal-title":"Psychological Science"},{"key":"2026033010380563100_bib26","first-page":"81","article-title":"The magical number seven, plus or minus two: Some limits on our capacity for processing information","author":"Miller","year":"1956"},{"key":"2026033010380563100_bib27","doi-asserted-by":"publisher","first-page":"Article 103954","DOI":"10.1016\/j.jobe.2021.103954","article-title":"Structural health monitoring of civil engineering structures by using the internet of things: A review","volume":"48","author":"Mishra","year":"2022","journal-title":"Journal of Building Engineering"},{"key":"2026033010380563100_bib28","doi-asserted-by":"publisher","first-page":"Article 1007886","DOI":"10.3389\/fbuil.2022.1007886","article-title":"Artificial intelligence in civil infrastructure health monitoring\u2014historical perspectives, current trends, and future visions","volume":"8","author":"Mondal","year":"2022","journal-title":"Frontiers in Built Environment"},{"key":"2026033010380563100_bib29","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.1109\/TSMC.2018.2830099","article-title":"Efficient deep CNN-based fire detection and localization in video surveillance applications","volume":"49","author":"Muhammad","year":"2019","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"key":"2026033010380563100_bib30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1098\/rsta.2023.0159","article-title":"Large language models as tax attorneys: a case study in legal capabilities emergence","volume":"382(2270)","author":"Nay","year":"2024","journal-title":"Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences"},{"key":"2026033010380563100_bib32","doi-asserted-by":"publisher","first-page":"7957","DOI":"10.18653\/v1\/2023.emnlp-main.494","article-title":"Automatic prompt optimization with \u201cGradient Descent\u201d and beam search","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","author":"Pryzant","year":"2023"},{"key":"2026033010380563100_bib33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.00020","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"2026033010380563100_bib34","doi-asserted-by":"publisher","first-page":"Aritcle 7","DOI":"10.1186\/2193-0414-2-7","article-title":"Fire evacuation in high-rise buildings: a review of human behaviour and modelling research","volume":"2","author":"Ronchi","year":"2013","journal-title":"Fire Science Reviews"},{"key":"2026033010380563100_bib35","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1016\/0010-0285(75)90024-9","article-title":"Family resemblances: studies in the internal structure of categories","volume":"7","author":"Rosch","year":"1975","journal-title":"Cognitive Psychology"},{"key":"2026033010380563100_bib36","doi-asserted-by":"publisher","first-page":"889","DOI":"10.1007\/s11554-020-01044-0","article-title":"Real-time video fire\/smoke detection based on CNN in antifire surveillance systems","volume":"18","author":"Saponara","year":"2020","journal-title":"Journal of Real-Time Image Processing"},{"key":"2026033010380563100_bib31","doi-asserted-by":"publisher","first-page":"Article 3161","DOI":"10.3390\/s23063161","article-title":"A YOLOv6-based improved fire detection approach for smart city environments","volume":"23","author":"Saydirasulovich","year":"2023","journal-title":"Sensors"},{"key":"2026033010380563100_bib37","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1109\/JPROC.2015.2494218","article-title":"Taking the human out of the loop: a review of Bayesian optimization","volume":"104","author":"Shahriari","year":"2016","journal-title":"Proceedings of the IEEE"},{"key":"2026033010380563100_bib38","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2023","journal-title":"Nature"},{"key":"2026033010380563100_bib39","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1016\/j.eng.2018.11.030","article-title":"Advances in computer vision-based civil infrastructure inspection and monitoring","volume":"5","author":"Spencer","year":"2019","journal-title":"Engineering"},{"key":"2026033010380563100_bib40","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203.11171","article-title":"Self-consistency improves chain-of-thought reasoning in language models","author":"Wang","year":"2023"},{"key":"2026033010380563100_bib41","doi-asserted-by":"publisher","first-page":"2817","DOI":"10.1007\/978-1-4939-2565-0_72","article-title":"Introduction to fire risk analysis","volume-title":"SFPE Handbook of Fire Protection Engineering","author":"Watts","year":"2016"},{"key":"2026033010380563100_bib42","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026033010380563100_bib43","article-title":"A prompt pattern catalog to enhance prompt engineering with ChatGPT","author":"White","year":"2023"},{"key":"2026033010380563100_bib44","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/j.psep.2019.05.016","article-title":"An intelligent fire detection approach through cameras based on computer vision methods","volume":"127","author":"Wu","year":"2019","journal-title":"Process Safety and Environmental Protection"},{"key":"2026033010380563100_bib45","article-title":"Large language models as optimizers","author":"Yang","year":"2024"},{"key":"2026033010380563100_bib46","article-title":"Tree of thoughts: Deliberate problem solving with large language models","author":"Yao","year":"2023"},{"key":"2026033010380563100_bib47","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1093\/jcde\/qwaf033","article-title":"Evaluating ChatGPT on Korea\u2019s BIM expertise exam and improving its performance through RAG","volume":"12","author":"Yu","year":"2025","journal-title":"Journal of Computational Design and Engineering"},{"key":"2026033010380563100_bib48","doi-asserted-by":"publisher","first-page":"Article 100103","DOI":"10.1016\/j.metrad.2024.100103","article-title":"Potential of multimodal large language models for data mining of medical images and free-text reports","volume":"2","author":"Zhang","year":"2024","journal-title":"Meta-Radiology"},{"key":"2026033010380563100_bib49","doi-asserted-by":"publisher","first-page":"Article 111","DOI":"10.3390\/f15010111","article-title":"A forest fire recognition method based on modified deep CNN model","volume":"15","author":"Zheng","year":"2024","journal-title":"Forests"},{"key":"2026033010380563100_bib50","doi-asserted-by":"publisher","first-page":"16795","DOI":"10.1109\/CVPR52688.2022.01631","article-title":"Conditional prompt learning for vision-language models","volume-title":"In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zhou","year":"2022"},{"key":"2026033010380563100_bib51","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"International Journal of Computer Vision"}],"container-title":["Journal of Computational Design and Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jcde\/advance-article-pdf\/doi\/10.1093\/jcde\/qwag022\/67300988\/qwag022.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/13\/3\/305\/67300988\/qwag022.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/13\/3\/305\/67300988\/qwag022.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T14:38:17Z","timestamp":1774881497000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jcde\/article\/13\/3\/305\/8514309"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,28]]},"references-count":51,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,2,28]]}},"URL":"https:\/\/doi.org\/10.1093\/jcde\/qwag022","relation":{},"ISSN":["2288-5048"],"issn-type":[{"value":"2288-5048","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,3]]},"published":{"date-parts":[[2026,2,28]]}}}