Generative AI for Urban Planning and Design: Progress Review and Future Perspectives

Chao Liu; Guoqing Li; Chengcheng Huang; Otthein Herzog; Helge Ritter; Shengxin Ma; Yu Ye

doi:10.1016/j.eng.2026.03.001

Engineering ›› :202603001 DOI: 10.1016/j.eng.2026.03.001

Research

research-article

Generative AI for Urban Planning and Design: Progress Review and Future Perspectives

Author information +

History +

PDF (4349KB)

Abstract

The integration of generative artificial intelligence (GenAI) into urban planning and design has rapidly advanced as a key research frontier in recent years. This study reviews the application and emerging trends of GenAI in different stages of planning and design, including theoretical understanding, spatial analysis, and generation and evaluation of planning and design. Specifically, ① theoretical understanding: GenAI can construct multimodal knowledge graphs that support a more systematic understanding of fragmented knowledge in planning and design by integrating heterogeneous textual, visual, and spatial data. ② Urban spatial analysis: GenAI can enhance analytic capacity and inclusiveness in spatial analysis. It enables efficient interpretation of current socioeconomic and spatial conditions from multimodal data and can simulate the reasoning of multiple stakeholders, including experts and the public. Although limited in mechanistic, rule-based analyses, it can be extended via prompt engineering and tool use, lowering technical barriers. ③ Planning and design generation: GenAI can assist practitioners in drafting text, generating design images, and producing simple three-dimensional models. However, it is not yet capable of independently producing comprehensive, regulation-compliant planning documents or spatial layouts. Thus, it should be regarded as a supplementary tool rather than a replacement for human expertise. ④ Planning and design evaluation: Through domain adaptation and knowledge integration, GenAI can evaluate planning texts, spatial performance, ecological performance, and other multicriteria dimensions. It also supports multistakeholder assessments via large language model-based agentic workflows, but does not yet reliably automate the iterative optimization of proposals. Although the use of GenAI in this field is still in its early stages, it demonstrates cross-process potential across the entire planning and design workflow. It is expected to accelerate the shift toward computational urban science, move practice from experience-oriented to engineering-oriented approaches, and enhance the efficiency and quality of public participation, thereby better aligning planning outcomes with diverse societal needs.

Keywords

Generative AI / Urban planning / Urban design / Computational methods / Artificial intelligence

Cite this article

Download citation ▾

Chao Liu, Guoqing Li, Chengcheng Huang, Otthein Herzog, Helge Ritter, Shengxin Ma, Yu Ye. Generative AI for Urban Planning and Design: Progress Review and Future Perspectives. Engineering 202603001 DOI:10.1016/j.eng.2026.03.001

登录浏览全文

4963

注册一个新账户忘记密码

References

Publishing order | Descend order by publishing year | Descend order by cited within

[1]	Kaplan A, Haenlein M. Siri, Siri, in my hand: who’s the fairest in the land? On the interpretations, illustrations, and implications of artificial intelligence. Bus Horiz 2019; 62(1):15-25.

[2]	Rosenblatt F. The perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev 1958; 65(6):386-408.

[3]	Newell A, Shaw JC, Simon HA. Report on a general problem solving program. Report. Pittsburgh: International Federation for Information Processing (IFIP); 1959.

[4]	Lindsay RK, Buchanan BG, Feigenbaum EA, Lederberg J. DENDRAL: a case study of the first expert system for scientific hypothesis formation. Artif Intell 1993; 61(2):209-61.

[5]	Jiang Y, Li X, Luo H, Yin S, Kaynak O. Quo vadis artificial intelligence? Discov Artif Intell 2022; 2(1):4.

[6]	Silver D, Schrittwieser J, Simonyan K, Antonoglou I, Huang A, Guez A, et al. Mastering the game of Go without human knowledge. Nature 2017; 550(7676):354-9.

[7]	Nah FFH, Zheng R, Cai J, Siau K, Chen L. Generative AI and ChatGPT: applications, challenges, and AI-human collaboration. J Inf Technol Case Appl Res 2023; 25(3):277-304.

[8]	Bengesi S, El-Sayed H, Sarker MK, Houkpati Y, Irungu J, Oladunni T. Advancements in generative AI: a comprehensive review of GANs, GPT, autoencoders, diffusion model, and transformers. IEEE Access 2024; 12:69812-37.

[9]	Feuerriegel S, Hartmann J, Janiesch C, Zschech P. Generative AI. Bus Inf Syst Eng 2024; 66(1):111-26.

[10]	Bishop CM. Pattern recognition and machine learning. Berlin: Springer Nature; 2006.

[11]	Goodfellow I, Bengio Y, Courville A. Deep learning. Cambridge: MIT Press; 2016.

[12]	Tomczak J, Welling M. VAE with a VampPrior. PMLR 2018; 84:1214-23.

[13]	Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative adversarial networks. Commun ACM 2020; 63(11):139-44.

[14]	Han K, Wang Y, Chen H, Chen X, Guo J, Liu Z, et al. A survey on vision transformer. IEEE Trans Pattern Anal Mach Intell 2023; 45(1):87-110.

[15]	Gozalo-Brizuela R, Garrido-Merchán EC. A survey of generative AI applications. arXiv:230602781; 2023.

[16]	Peng ZR, Lu KF, Liu Y, Zhai W. The pathway of urban planning AI: from planning support to plan-making. J Plann Educ Res 2023; 44(4):1-17.

[17]	Wang D, Lu CT, Fu Y. Towards automated urban planning: when generative and ChatGPT-like AI meets urban planning. arXiv:230403892; 2023.

[18]	Goetz EG, Williams RA, Damiano A. Whiteness and urban planning. J Am Plann Assoc 2020; 86(2):142-56.

[19]	Jacobs J. The death and life of great American cities. New York City: Random House Publishing; 2012.

[20]	Lynch K, Lynch K, Lynch KM, Lynch K. The image of the city. Cambridge: MIT Press; 1960.

[21]	Lynch K. Good city form. Cambridge: MIT press; 1984.

[22]	Abd Elrahman AS, Asaad M. Urban design & urban planning: a critical analysis to the theoretical relationship gap. Ain Shams Eng J 2021; 12(1):1163-73.

[23]	Alexander C. A city is not a tree. 50th anniversary ed. Portland: Sustasis Press; 2015.

[24]	Batty M. The new science of cities. Cambridge: MIT Press; 2013.

[25]	Ritter H, Herzog O, Rothermel K, Cohn AG, Wu Z. City models: past, present and future prospects. Front Urban Rural Plan 2025; 3:7.

[26]	Zhen F, Zhang S, Qin X, Xi G. From informational empowerment to comprehensive empowerment: exploring the ideas of smart territorial spatial planning. J Nat Res 2019; 34(10):2060-72 [Chinese].

[27]	Massaro M, Dumay J, Guthrie J. On the shoulders of giants: undertaking a structured literature review in accounting. Account Audit Account J 2016; 29(5):767-801.

[28]	Rittel HW, Webber MM. Dilemmas in a general theory of planning. Policy Sci 1973; 4(2):155-69.

[29]	Batty M. Digital twins in city planning. Nat Comput Sci 2024; 4(3):192-9.

[30]	Kar S, Roy C, Das M, Mullick S, Saha R. AI horizons: unveiling the future of generative intelligence. Int J Adv Res Sci Commun Technol 2023:387-91.

[31]	Mikolov T, Karafiát M, Burget L, Černocký J, Khudanpur S. Recurrent neural network based language model. In: Proceedings of the 11th annual conference of the international speech communication association (ISCA), INTERSPEECH 2010, 2010 September 26-30, Chiba, Japan. Grenoble: ISCA; 2010. p. 1045-8.

[32]	Cahuantzi R, Chen X, Güttel S. A comparison of LSTM and GRU networks for learning symbolic sequences. In: Arai K, editor. Intelligent computing. SAI 2023. Lecture notes in networks and systems. Berlin: Springer; 2023. p. 771-85.

[33]	Vinyals O, Toshev A, Bengio S, Erhan D. Show and tell:a neural image caption generator. In: Proceedings of the 2015 IEEE conference on computer vision and pattern recognition (CVPR), 2015 Jun 7-12, Boston, MA, USA. New York City: IEEE; 2015. p. 3156-64.

[34]	Fu R, Zhang Z, Li L. Using LSTM and GRU neural network methods for traffic flow prediction. In: Proceedings of the 2016 31st youth academic annual conference of chinese association of automation (YAC), 2016 Nov 11-13, Wuhan, China. New York City:IEEE; 2016. p. 324-8.

[35]	Pal U, Mondal S, Mondal MA, Kundu R, Roy S, Das S, et al. A hybrid CNN-LSTM approach for accident tweet classification. Int Res J Multidiscip Scope 2025; 6(3):1153-67.

[36]	Kong J, Huang J, Yu H, Deng H, Gong J, Chen H. RNN-based default logic for route planning in urban environments. Neurocomputing 2025; 338:307-20.

[37]	Kingma DP, Welling M. Auto-encoding variational bayes [Internet]. Golden Valley: INSPRIE; 2013 Dec 20 [cited 2026 Jan 15]. Available from: https://inspirehep.net/literature/1706699.

[38]	Chouikhi F, Ben Abbes A, Riadh FI. Supervised desertification classification using Siamese variational autoencoder. Int J Image Data Fusion 2025; 16(1):2476544.

[39]	Wang JK, Johnson BA, Chen Z, Zhang H, Szanto D, Woods B, et al. Quantifying the spatial patterns of retinal ganglion cell loss and progression in optic neuropathy by applying a deep learning variational autoencoder approach to optical coherence tomography. Front Ophthalmol 2025; 4:1497848.

[40]	Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative adversarial nets. In: Proceedings of the 28th international conference on neural information processing systems, 2014 Dec 8-13, Montreal, BC, Canada. Cambridge: MIT Press; 2014. p. 2672-80.

[41]	Du Z, Shen H, Li X, Wang M. 3D building fabrication with geometry and texture coordination via hybrid GAN. J Ambient Intell Humaniz Comput 2022; 13(11):5177-88.

[42]	Chang KH, Cheng CY, Luo J, Murata S, Nourbakhsh M, Tsuji Y. Building-GAN:graph-conditioned architectural volumetric design generation. In: Proceedings of the 2021 IEEE/CVF international conference on computer vision (ICCV 2021), 2021 Oct 11-17, online. New York City: IEEE; 2021. p. 11936-45.

[43]	Qian W, Xu Y, Li H. A self-sparse generative adversarial network for autonomous early-stage design of architectural sketches. Comput Aided Civ Infrastruct Eng 2022; 37(5):612-28.

[44]	Park C, No W, Choi J, Kim Y. Development of an AI advisor for conceptual land use planning. Cities 2023; 138:104371.

[45]	Wang D, Liu K, Huang Y, Sun L, Du B, Fu Y. Automated urban planning aware spatial hierarchies and human instructions. Knowl Inf Syst 2023; 65(3):1337-64.

[46]	Xiong Y, Chai C, Gan YS, Chong HY. 3D generative early-stage building design from 2D images: integration of multimodal data with GAN (3DMM-GAN). Innov Infrastruct Solut 2025; 10(5):162.

[47]	Quan SJ. Urban-GAN: an artificial intelligence-aided computation system for plural urban design. Environ Plan B Urban Anal City Sci 2022; 49(9):2500-15.

[48]	Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. In: Proceedings of the 31st international conference on neural information processing systems (NIPS 2017), 2017 Dec 4-9, Long Beach, CA, USA. Red Hook: Curran Associates, Inc.; 2017. p. 5998-6008.

[49]

Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, et al. Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF international conference on computer vision (ICCV), 2021 Oct 10-17, Montreal, QC, Canada. Los Alamitos: IEEE Computer Society; 2021. p. 9992-10002.

[50]	Fu X. Natural language processing in urban planning: a research agenda. J Plann Lit 2024; 39(3):395-407.

[51]	Zhu H, Zhang W, Huang N, Li B, Niu L, Fan Z, et al. PlanGPT: enhancing urban planning with tailored language model and efficient retrieval. arXiv:2402.19273; 2024.

[52]	Zhao C, Ogawa Y, Chen S, Sekimoto Y. Scene level people flow trend prediction by Swin transformer. In: Proceedings of the IEEE international geoscience and remote sensing symposium (IGARSS 2022), 2022 Jul 17-22, Kuala Lumpur, Malaysia. New York City: IEEE; 2022. p. 2434-7.

[53]	Qiu Y, Wu M, Huang Q, Kang Y. Do you know your neighborhood? Integrating street view images and multi-task learning for fine-grained multi-class neighborhood wealthiness perception prediction. Cities 2025; 158:105703.

[54]	Kumar KM. RoadTransNet: advancing remote sensing road extraction through multi-scale features and contextual information. Signal Image Video Process 2024; 18(3):2403-12.

[55]	Radford A, Narasimhan K, Salimans T, Sutskever I. Improving language understanding by generative pre-training; 2018, in press.

[56]	Devlin J, Chang MW, Lee K, Toutanova K. BERT: pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805; 2019.

[57]	Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I. Language models are unsupervised multitask learners. arXiv:2005.14165; 2019.

[58]

Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, et al. Language models are few-shot learners. In: Proceedings of the 34th annual conference on neural information processing systems (NeurIPS 2020), 2020 Dec 6-12, Vancouver, BC, Canada. Red Hook: Curran Associates, Inc.; 2020. p. 1877-901.

[59]	Chowdhery A, Narang S, Devlin J, Bosma M, Mishra G, Roberts A, et al. PaLM: scaling language modeling with pathways. arXiv:2204.02311; 2022.

[60]	Open AI, Achiam J, Adler S, Agarwal S, Ahmad L, Akkaya I, et al. GPT-4 technical report. arXiv:2303.08774; 2024.

[61]	Jin Y, Ma J. Large language model as parking planning agent in the context of mixed period of autonomous vehicles and human-driven vehicles. Sustain Cities Soc 2024; 117:105940.

[62]	Peng C, Yang X, Chen A, Yu Z, Smith KE, Costa AB, et al. Generative large language models are all-purpose text analytics engines: text-to-text learning is all your need. J Am Med Inform Assoc 2024; 31(9):1892-903.

[63]	Kalyuzhnaya A, Mityagin S, Lutsenko E, Getmanov A, Aksenkin Y, Fatkhiev K, et al. LLM agents for smart city management: enhancing decision support through multi-agent AI systems. Smart Cities 2025; 8(1):19.

[64]	Ramesh A, Pavlov M, Goh G, Gray S, Voss C, Radford A, et al. Zero-shot text-to-image generation. arXiv:2102.12092; 2021.

[65]

Rombach R, Blattmann A, Lorenz D, Esser P, Ommer B. High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), 2022 Jun 18-24, New Orleans, LA, USA. Los Alamitos: IEEE Computer Society; 2022. p. 10684-95.

[66]	Peng B, Liang CX, Bi Z, Liu M, Zhang Y, Wang T, et al. From noise to nuance: advances in deep generative image models. arXiv:2412.09656; 2024.

[67]	Yang Y, Zeng J, Yin J, Wu P, Xu G, Jing C, et al. Metro stations as catalysts for land use patterns: evidence from Wuhan Line 11. Sustainability 2024; 16(15):6320.

[68]

Zhuang J, Li G, Xu H, Xu J, Tian R. Text-to-city controllable 3D urban block generation with latent diffusion model. In: Proceedings of the 29th international conference of the association for computer-aided architectural design research in Asia (CAADRIA 2024), vol. 2, 2024 Apr 18-20, Hong Kong, China. Hong Kong: CAADRIA; 2024. p. 169-78.

[69]	Wang Z, Hao Z, Zhang Y, Feng Y, Guo Y. UP-diff: latent diffusion model for remote sensing urban prediction. IEEE Geosci Remote Sens Lett 2025; 22:1-5.

[70]	Huang L, Oki T. Enhancing people’s walking preferences in street design through generative artificial intelligence and crowdsourcing surveys: the case of Tokyo. Environ Plan B Urban Anal City Sci 2025;23998083251327405.

[71]

Blecic I, Saiu V, Trunfio GA. Enhancing urban walkability assessment with multimodal large language models. In: Gervasi O, Murgante B, Garau C, Taniar D, Rocha A, Lago MNF, editors. Computational science and its applications—ICCSA 2024 Workshops. Part V. Cham: Springer International Publishing AG; 2024. p. 394-411.

[72]

Kim H, Kang M, Choi H, Cheong YG. Dataset generation for Korean urban parks analysis with large language models. In: Proceedings of the 33rd ACM international conference on information and knowledge management (CIKM 2024), 2024 Oct 21-25, Boise, ID, USA. New York City: Association Computing Machinery (ACM); 2024. p. 5375-9.

[73]	Lin H, Hong D, Ge S, Luo C, Jiang K, Jin H, et al. RS-MoE: a vision-language model with mixture of experts for remote sensing image captioning and visual question answering. IEEE Trans Geosci Remote Sens 2025; 63:5614918.

[74]

Lewis P, Perez E, Piktus A, Petroni F, Karpukhin V, Goyal N, et al. Retrieval-augmented generation for knowledge-intensive NLP tasks. In: Larochelle H, Ranzato M, Hadsell R, Balcan MF, Lin H, editors. Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, 2020 Dec 6-12, online. San Diego: Neural Information Processing Systems Foundation; 2020. p. 9459-74.

[75]	Pan S, Luo L, Wang Y, Chen C, Wang J, Wu X. Unifying large language models and knowledge graphs: a roadmap. IEEE Trans Knowl Data Eng 2024; 36(7):3580-99.

[76]	Tsaneva S, Dessì D, Osborne F, Sabou M. Knowledge graph validation by integrating LLMs and human-in-the-loop. Inf Process Manage 2025; 62(5):104145.

[77]	Ji S, Pan S, Cambria E, Marttinen P, Yu PS. A survey on knowledge graphs: representation, acquisition, and applications. IEEE Trans Neural Netw Learn Syst 2022; 33(2):494-514.

[78]	Zou X, Yan Y, Hao X, Hu Y, Wen H, Liu E, et al. Deep learning for cross-domain data fusion in urban computing: taxonomy, advances, and outlook. Inf Fusion 2025; 113:102606.

[79]	Anthony JB. A case-based reasoning recommender system for sustainable smart city development. AI Soc 2021; 36(1):159-83.

[80]	Li H, Yang R, Xu S, Xiao Y, Zhao H. Intelligent checking method for construction schemes via fusion of knowledge graph and large language models. Buildings 2024; 14(8):2502.

[81]	Noor Asmat B, Bilal HSM, Uddin MI, Karim FK, Mostafa SM. Utilizing conditional GANs for synthesis of equilibrated hyperspectral data to enhance classification and mitigate majority class bias. IEEE Access 2025; 13:49271-89.

[82]	Chen C, Chen X, Ye Y. Measuring the unmeasurable:an evaluation method addressing urban texture harmony intelligently. In: Djokic V, Djordjevic A, Milojevic M, Milovanovic A, Pesic M, editors. Praxis of urban morphology, part 2. Belgrade: University of Belgrade, 2023. p. 187-97.

[83]

Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, et al. Learning transferable visual models from natural language supervision. In: Meila M, Zhang T, editors. Proceedings of the 38th international conference on machine learning, ICML 2021, 2021 Jul 18-24, online. San Diego: J Mach Learn Res; 2021. p. 8748-63.

[84]	Fu X, Wang R, Li C. Can ChatGPT evaluate plans? J Am Plann Assoc 2024; 90(3):525-36.

[85]	Zhang R, El-Gohary N. Transformer-based approach for automated context-aware IFC-regulation semantic information alignment. Autom Constr 2023; 145:104540.

[86]	Lu Z, Wang W, Guo T, Li Y, Wang F. Decoding urban policies: NLP-driven concise explanations. Environ Plan B Urban Anal City Sci 2025;23998083251321981.

[87]	Hou C, Zhang F, Li Y, Li H, Mai G, Kang Y, et al. Urban sensing in the era of large language models. Innovation 2025; 6(1):100749.

[88]	Jang KM, Kim J. Multimodal large language models as built environment auditing tools. Prof Geogr 2025; 77(1):84-90.

[89]	Ramalingam SP, Kumar V. Building usage prediction in complex urban scenes by fusing text and facade features from street view images using deep learning. Build Environ 2025; 267:112174.

[90]	Ma H, Zheng H. Text semantics to image generation:a method of building facades design base on stable diffusion model. In: Yan C, Chai H, Sun T, Yuan PF, editors. Phygital intelligence Singapore: Springer Nature Singapore; 2024. p. 24-34.

[91]	Dortheimer J, Martelaro N, Sprecher A, Schubert G. Evaluating large-language-model chatbots to engage communities in large-scale design projects. Artif Intell Eng Des Anal Manuf 2024; 38:e4.

[92]

Liu J, Xue Y, Duarte J, Shekhawat K, Zhou Z, Huang X. End-to-end graph-constrained vectorized floorplan generation with panoptic refinement. In: Avidan S, Brostow G, Cissé M, Farinella GM, Hassner T, editors. Computer vision—ECCV 2022. Proceedings of the 17th European conference, 2022 Oct 23-27, Tel Aviv, Israel. Cham: Springer Nature Switzerland; 2022. p. 547-62.

[93]	Zhang H, Blasetti E. 3D architectural form style transfer through. Mach Learn 2020; 2:661-70.

[94]	Huang C, Zhang G, Yao J, Wang X, Calautit JK, Zhao C, et al. Accelerated environmental performance-driven urban design with generative adversarial network. Build Environ 2022; 224:109575.

[95]	Cui X, Feng X, Sun S. Learning to generate urban design images from the conditional latent diffusion model. IEEE Access 2024; 12:89135-43.

[96]	Cai S, Cui W. Evade ChatGPT detectors via a single space; 2023.

[97]	Pena MLC, Carballal A, Rodriguez-Fernandez N, Santos I, Romero J. Artificial intelligence applied to conceptual design. A review of its use in architecture. Autom Constr 2021; 124:103550.

[98]	Lin J, Zhou Y, Zhe Z, Lu X. Research and application of intelligent design review. Eng Mech 2023; 40(7):25-38 [Chinese].

[99]	Liu Y, Hu K, Deng Q. Artificial intelligence-assisted case-based design: a case study on urban texture darning surrounding the ancient city of Nantou in Shenzhen. South Archit 2023;6:20-7 [Chinese].

[100]

Ampanavos S, Malkawi A. Early-phase performance-driven design using generative models. In: Gerber D, Pantazis E, Bogosian B, Nahmad A, Miltiadis C, editors. Computer-aided architectural design: design imperatives-the future is now. Cham: Springer International Publishing; 2022. p. 87-106.

[101]

Rane N, Choudhary S, Rane J. Bard, and leading-edge generative artificial intelligence in architectural design and engineering: applications, framework, and challenges. Int J Arch Plan 2023; 3(2):92-124.

[102]

Sun S. Transformation from urban and rural planning to territory spatial planning. Front Urban Rural Plan 2023; 1(1):2.

[103]

Phua SZ, Hofmeister M, Tsai YK, Peppard O, Lee KF, Courtney S, et al. Fostering urban resilience and accessibility in cities: a dynamic knowledge graph approach. Sustain Cities Soc 2024; 113:105708.

[104]

Sheth A, Padhee S, Gyrard A. Knowledge graphs and knowledge networks: the story in brief. IEEE Internet Comput 2019; 23(4):67-75.

[105]

Tan J, Qiu Q, Guo W, Li T. Research on the construction of a knowledge graph and knowledge reasoning model in the field of urban traffic. Sustainability 2021; 13(6):3191.

[106]

Zhang Y, Liu W, Chen L, Zhou K. Research on the application of knowledge graph technology in urban management decision support system. In: Proceedings of the 2024 international conference on decision science & management, 2024 Oct 18-20, Singapore City, Singapore. New York City: Association for Computing Machinery (ACM); 2024. p. 125-134.

[107]

Xu Y, Huang Y, Wang H, Liu C, Xie X, Wang H. KnowSite:leveraging urban knowledge graph for site selection. In: Proceedings of the 31st ACM international conference on advances in geographic information systems, 2023 Nov 13-16, Hamburg, Germany. New York City: Association for Computing Machinery (ACM); 2023. p. 1-4.

[108]

Liu H, Perl Y, Geller J. Concept placement using BERT trained by transforming and summarizing biomedical ontology structure. J Biomed Inform 2020; 112:103607.

[109]

Kommineni VK, König-Ries B, Samuel S. From human experts to machines: an LLM supported approach to ontology and knowledge graph construction. 2024. arXiv:2403.08345.

[110]

Zhao M, Pan H. Construction logic and implementation strategies of spatial planning system of China. Front Urban Rural Plan 2023; 1(1):6.

[111]

Zhao H, Pan Y, Yang F. Research on information extraction of technical documents and construction of domain knowledge graph. IEEE Access 2020; 8:168087-98.

[112]

Yu H, Li H, Mao D, Cai Q. A relationship extraction method for domain knowledge graph construction. World Wide Web 2020; 23(2):735-53.

[113]

Saxena A, Tripathi A, Talukdar P. Improving multi-hop question answering over knowledge graphs using knowledge base embeddings. Proceedings of the 58th annual meeting of the association for computational linguistics, 2020 Jul 5-10, Online. Stroudsburg: Association for Computational Linguistics; 2020. p. 4498-507.

[114]

McPhearson T, Haase D, Kabisch N, Gren Å. Advancing understanding of the complex nature of urban systems. Ecol Indic 2016; 70:566-73.

[115]

Crooks AT, Heppenstall AJ. Introduction to agent-based modelling. In: Heppenstall AJ, Crooks AT, See LM, Batty M, editors. Agent-based models of geographical systems. Dordrecht: Springer, 2012. p. 85-105.

[116]

Ma Q, Xue X, Zhou D, Yu X, Liu D, Zhang X, et al. Computational experiments meet large language model based agents: a survey and perspective. arXiv:2402.00262; 2024.

[117]

Gallotti R, Sacco P, De Domenico M. Complex urban systems: challenges and integrated solutions for the sustainability and resilience of cities. Complexity 2021; 2021(1):1782354.

[118]

Park JS, O’Brien J, Cai CJ, Morris MR, Liang P, Bernstein MS. Generative agents:interactive simulacra of human behavior. In: Proceedings of the 36th annual ACM symposium on user interface software and technology, 2023 Oct 29-Nov 1, San Francisco, CA, USA. New York City: Association for Computing Machinery (ACM); 2023. p. 1-22.

[119]

Lu Y, Aleta A, Du C, Shi L, Moreno Y. LLMs and generative agent-based models for complex systems research. Phys Life Rev 2024; 51:283-93.

[120]

Yan Y, Zeng Q, Zheng Z, Yuan J, Feng J, Zhang J, et al. Opencity: a scalable platform to simulate urban activities with massive LLM agents. arXiv:241021286; 2024.

[121]

Glake D, Panse F, Ritter N, Clemen T, Lenfers U. Data management in multi-agent simulation systems from challenges to first solutions. BTW2021—database systems for business, technology and web. Berlin: Digital Bibliothek; 2021.

[122]

Long L, Wang R, Xiao R, Zhao J, Ding X, Chen G, et al. On LLMs-driven synthetic data generation, curation, and evaluation:a survey. In: Ku LW, Martins A, Srikumar V, editors. Proceedings of the 2024 conference of the association for computational linguistics, 2024 Aug 11-16, Bangkok, Thailand. Stroudsburg: Association for Computational Linguistics; 2024. p. 11065-82.

[123]

Wu F. Planning for growth:urban and regional planning in China. New York City: Routledge; 2015.

[124]

Healey P. Collaborative planning: Shaping places in fragmented societies. Vancouver: UBC Press; 1997.

[125]

Healey P. Collaborative planning in perspective. Plann Theory 2003; 2(2):101-23.

[126]

Gao C, Lan X, Li N, Yuan Y, Ding J, Zhou Z, et al. Large language models empowered agent-based modeling and simulation: a survey and perspectives. Humanit Soc Sci Commun 2024; 11(1):1259.

[127]

Feng J, Zhang J, Liu T, Zhang X, Ouyang T, Yan J, et al. CityBench: evaluating the capabilities of large language models for urban tasks. arXiv:2502.12345; 2025.

[128]

Bougie N, Watanabe N. CitySim: modeling urban behaviors and city dynamics with large-scale LLM-driven agent simulation. arXiv:2503.67890; 2025.

[129]

Zhang Y, Lin Y, Tian L, Yang X. Leveraging LLM-based multi-agent simulations to boost participatory design education: an experimental exploration in residential area design. Sustain Cities Soc 2025; 131:106761.

[130]

Zhou Z, Lin Y, Jin D, Li Y. Large language model for participatory urban planning. arXiv:2402.17161; 2024.

[131]

Lin J, Chen X, Wei X. Coordination problems of spatial planning in China: international lessons and experiences. Mod Urban Res 2011; 26:15-21.

[132]

Wang R, Huang C, Ye Y. Measuring street quality: a human-centered exploration based on multi-sourced data and classical urban design theories. Buildings 2024; 14(11):3332.

[133]

Zhang A, Chen Y, Sheng L, Wang X, Chua TS. On generative agents in recommendation. In: Proceedings of the 47th International ACM SIGIR conference on research and development in information retrieval, 2024 Jul 14-18, Washington, DC, USA. New York City: Association for Computing Machinery (ACM); 2024. p. 1807-17.

[134]

Innes JE, Booher DE. Reframing public participation: strategies for the 21st century. Plann Theory Pract 2004; 5(4):419-36.

[135]

Berke P, Godschalk D. Searching for the good plan: a meta-analysis of plan quality studies. J Plann Lit 2009; 23(3):227-40.

[136]

Stevens MR, Lyles W, Berke PR. Measuring and reporting intercoder reliability in plan quality evaluation research. J Plann Educ Res 2014; 34(1):77-93.

[137]

Brody SD. Are we learning to make better plans? A longitudinal analysis of plan quality associated with natural hazards. J Plann Educ Res 2003; 23(2):191-201.

[138]

Wu Z, Pan Y, Ye Q, Kong L. The city intelligence quotient (city IQ) evaluation system: conception and evaluation. Engineering 2016; 2(2):196-211.

[139]

Maldonado D, Cruz E, Abad Torres J, Cruz PJ, Gamboa Benitez SP. Multi-agent systems: a survey about its components, framework and workflow. IEEE Access 2024; 12:80950-75.

[140]

Li X, Wang S, Zeng S, Wu Y, Yang Y. A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges. Vicinagearth 2024; 1(1):9.

[141]

Li T, Zhang G, Do QD, Yue X, Chen W. Long-context LLMs struggle with long in-context learning. arXiv:2404.02060; 2024.

[142]

Petroni F, Lewis P, Piktus A, Rocktäschel T, Wu Y, Miller AH, et al. How context affects language models’ factual predictions. arXiv:2005.04611; 2020.

[143]

Mallen A, Asai A, Zhong V, Das R, Khashabi D, Hajishirzi H. When not to trust language models: investigating effectiveness of parametric and non-parametric memories. arXiv:2212.10511; 2023.

[144]

Liu NF, Lin K, Hewitt J, Paranjape A, Bevilacqua M, Petroni F, et al. Lost in the middle: how language models use long contexts. arXiv:2307.03172; 2023.

[145]

He J, Pan K, Dong X, Song Z, Liu Y, Sun Q, et al. Never lost in the middle: mastering long-context question answering with position-agnostic decompositional training. arXiv:2404.07396; 2024.

[146]

Munkhdalai T, Faruqui M, Gopal S. Leave no context behind: efficient infinite context transformers with infini-attention. arXiv:2404.07143; 2024.

[147]

Li Z, Li C, Zhang M, Mei Q, Bendersky M. Retrieval augmented generation or long-context LLMs? A comprehensive study and hybrid approach. arXiv:2406.15402; 2024.

[148]

Hsieh CY, Chuang YS, Li CL, Wang Z, Le L, Kumar A, et al. Found in the middle:calibrating positional attention bias improves long context utilization. In: Ku LW, Martins A, Srikumar V, editors. Proceedings of the 2024 conference of the association for computational linguistics (ACL), 2024 Aug 11-16, Bangkok, Thailand. Stroudsburg: ACL; 2024. p. 14982-95.

[149]

Wei G, Wu Z, Wang Y, Xu H, Juan Y, Zhen H, et al. AIGC assisted urban design: a theoretical model. Urban Plan Forum 2023;02:12-8 [Chinese].

[150]

Wu C, Ye Y, Gao F, Ye X. Using street view images to examine the association between human perceptions of locale and urban vitality in Shenzhen, China. Sustain Cities Soc 2023; 88:104291.

[151]

Zandavali BA, Turkienicz B. Cellular automata:bridge between building variability and urban form control. In: Proceedings of the symposium on simulation for architecture and urban design, 2018 Jun 4-7, Delft, The Netherlands. San Diego: Society for Computer Simulation International; 2018. p. 1-8.

[152]

Toulkeridou V. Steps towards AI augmented parametric modeling systems for supporting design exploration. In: Proceedings of the 37th education and research in computer aided architectural design in Europe and XXIII Iberoamerican society of digital graphics joint conference, 2019 Nov 5-8, Porto, Portugal. Brussels: Education and Research in Computer Aided Architectural Design in Europe; 2019.

[153]

Tan WR, Chan CS, Aguirre HE, Tanaka K. ArtGAN: artwork synthesis with conditional categorical GANs. In: Proceedings of the 2017 IEEE international conference on image processing (ICIP), 2017 Sep 17-20, Beijing, China. Piscataway: IEEE; 2017. p. 3760-4.

[154]

Yang J, Shao D, Wang P, Yin S, Murong Z. Integration, topology, and translation: an in-depth analysis method of urban form based on knowledge map. City Plan Rev 2022; 47:57-67.

[155]

Cai T, Duan J. Construction and application of characteristic townscape knowledge graph based on space gene theory. Cities 2025; 167:106289.

[156]

Zheng Y, Liu L, Lin Y, Feng J, Zhang G, Jin D, et al. UrbanPlanBench: a comprehensive urban planning benchmark for evaluating large language models. arXiv:2504.21027; 2025.

[157]

Lan H. Interpretable multimodal framework for human-centered street assessment: integrating visual-language models for perceptual urban diagnostics. arXiv:2506.05087; 2025.

[158]

Wang X, Ling X, Zhang T, Li X, Wang S, Li Z, et al. Optimizing and fine-tuning large language model for urban renewal. arXiv:2311.15490; 2023.

[159]

Yang J. Exploration on theoretical paradigm of all-digital urban design. Urban Plan Int 2018; 33(1):7-21 [Chinese].

[160]

Wang J. Digital urban design based on human-computer interaction: discussion on the fourth generation of urban design. Urban Plan Int 2018; 33(1):1-6 [Chinese].

[161]

Ramalingam SP, Kumar V. Automatizing the generation of building usage maps from geotagged street view images using deep learning. Build Environ 2023; 235:110215.

[162]

Xu Q, Liu Y, Wang D, Huang S. Automatic recognition of cross-language classic entities based on large language models. npj Herit Sci 2025; 13(1):59.

[163]

Abdurahman S, Salkhordeh Ziabari A, Moore AK, Bartels DM, Dehghani M. A primer for evaluating large language models in social-science research. Adv Methods Pract Psychol Sci 2025; 8(2):25152459251325174.

[164]

Zhu H, Chang J, An X, Li S. Global and local feature extraction of urban historical spatial perception using large language models: a case study of Harbin Central Street District. Cities 2025; 165:106183.

[165]

Hao Y, Xie D. A multi-LLM-agent-based framework for economic and public policy analysis. arXiv:250216879; 2025.

[166]

Zhang Z, Lian J, Ma C, Qu Y, Luo Y, Wang L, et al. TrendSim:simulating trending topics in social media under poisoning attacks with LLM-based multi-agent system. In: Proceedings of the 2025 annual conference of the nations of the Americas chapter of the association for computational linguistics, 2025 Apr 29-May 4, Albuquerque, New Mexico. Stroudsburg: Association for Computational Linguistics (ACL); 2025. p. 2930-49.

[167]

Maceda LL, Llovido JL, Artiaga MB, Abisado MB. Classifying sentiments on social media texts: a GPT-4 preliminary study. In: Proceedings of the 2023 7th international conference on natural language processing and information retrieval (NLPIR), 2023 Dec 15-17, Bangkok, Thailand. New York City: Association for Computing Machinery (ACM); 2023. p. 19-24.

[168]

Zhang Y, Li J, Wang Z, He Z, Guan Q, Lin J, et al. Geospatial large language model trained with a simulated environment for generating tool-use chains autonomously. Int J Appl Earth Obs Geoinf 2025; 136:104312.

[169]

Yu D, Wan B, Sheng Q. Automated generation of urban spatial structures based on stable diffusion and CoAtNet models. Buildings 2024; 14(12):3720.

[170]

Jo H, Lee JK, Lee YC, Choo S. Generative artificial intelligence and building design: early photorealistic render visualization of façades using local identity-trained models. J Comput Des Eng 2024; 11(2):85-105.

[171]

He M, Liang Y, Wang S, Zheng Y, Wang Q, Zhuang D, et al. Generative AI for urban design: a stepwise approach integrating human expertise with multimodal diffusion models. arXiv:2505.24260; 2025.

[172]

Xu S, Zhang J, Li Y. Knowledge-driven and diffusion model-based methods for generating historical building facades: a case study of traditional Minnan residences in China. Information 2024; 15:344.

[173]

Meier DS. Generative modeling as a tool in urban riverfront design; an exploration of parametric design in landscape architecture [dissertation]. Ohio: The Ohio State University; 2012.

[174]

Cai C, Li B, Zhang Q, Wang X, Biljecki F, Herthogs P. Bi-directional mapping of morphology metrics and 3D city blocks for enhanced characterization and generation of urban form. Sustain Cities Soc 2025; 129:106441.

[175]

Xu J, Wang C, Zhao Z, Liu W, Ma Y, Gao S. CAD-MLLM: unifying multimodality-conditioned CAD generation with MLLM. arXiv:2411.04954; 2025.

[176]

Can J, Zhe Z, Xiong L, Jiarui LIN, Zhiliang MA, Xinzheng LU. A new interaction paradigm for building design driven by large language model: proof of concept with Rhino7. J Graph 2024; 45:594.

[177]

Sbiruani H. The urban design process. New York City: Van Nostrand Reinhold Company; 2010.

[178]

Karpathy A. Power to the people: how LLMs flip the script on technology diffusion [Internet]. Bastrop: X.com; 2025 Apr 8 [cited 2025 Sep 27]. Available from: https://karpathy.bearblog.dev/power-to-the-people/.

[179]

Li Z, Ning H. Autonomous GIS: the next-generation AI-powered GIS. Int J Digit Earth 2023; 16(2):4668-86.

[180]

Tian L, Yang X, Zhang Y, Lin Y. Exploration of innovative urban-rural planning and design education driven by “professional knowledge + artificial intelligence”: a case study of residential area planning. Urban Plan Forum 2024;5:71-8 [Chinese].

[181]

Wu Z. Intelligent planning. Shanghai: Shanghai Scientific & Technical Publishers; 2020. Chinese.

[182]

Zhang J, Hu J, Khayatkhoei M, Ilievski F, Sun M. Exploring perceptual limitation of multimodal large language models. arXiv:2402.07384; 2024.

[183]

El Banani M, Raj A, Maninis KK, Kar A, Li Y, Rubinstein M, et al. Probing the 3D awareness of visual foundation models. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, CVPR 2024—Workshops, 2024 Jun 17-18, Seattle, WA, USA. Los Alamitos: IEEE Computer Society; 2024. p. 21795-806.

[184]

Sun W, Zhang C, Zhang X, Yu X, Huang Z, Chen P, et al. Beyond instruction following: evaluating inferential rule following of large language models. arXiv:240708440; 2024.

[185]

Weber RE, Mueller C, Reinhart C. Automated floorplan generation in architectural design: a review of methods and applications. Autom Constr 2022; 140:104385.

[186]

Ma Y, Liu S, Ma A, Wu X, Leng D, Yin Y. HiCo: hierarchical controllable diffusion model for layout-to-image generation. Adv Neural Inf Process Syst 2024; 37:128886-910.

[187]

Shan C, Guo L, Chen H. Knowledge guided controllable diffusion for enhanced autonomous driving scenarios generation. Neurocomputing 2025; 648:130616.

[188]

Li X. A review of prominent paradigms for LLM-based agents:tool use, planning (including RAG), and feedback learning. In: Rambow O, Wanner L, Apidianaki M, Al-Khalifa H, Eugenio BD, Schockaert S, editors. Proceedings of the 31st international conference on computational linguistics, 2025 Jan 19-24, Abu Dhabi, UAE. Abu Dhabi: Association for Computational Linguistics (ACL); 2025. p. 9760-79.

[189]

Luo H, Zhang Z, Zhu Q, Houda Ben Ameur NE, Liu X, Ding F, et al. Using large language models to investigate cultural ecosystem services perceptions: a few-shot and prompt method. Landsc Urban Plan 2025; 258:105323.

[190]

Bosco G, Riccardi V, Sciarrone A, D’Amore R, Visvizi A. AI-driven innovation in smart city governance: achieving human-centric and sustainable outcomes. Transform Gov People Process Policy; 2024, in press.

[191]

Taeihagh A. Governance of generative AI. Policy Soc 2025; 44(1):1-22.

[192]

Tao Y, Viberg O, Baker RS, Kizilcec RF. Cultural bias and cultural alignment of large language models. PNAS Nexus 2024; 3(9):346.

[193]

Atari M, Xue M, Park P, Blasi D, Henrich J. Which humans? [Internet]. Cambridge: Department of Human Evolutionary Biology, Harvard University; [cited 2026 Jan 16]. Available from: https://coevolution.fas.harvard.edu/publications/which-humans.

[194]

Yao J, Yi X, Wang X, Gong Y, Xie X. Value fulcra: mapping large language models to the multidimensional spectrum of basic human values. arXiv:231110766; 2023.

[195]

Wang X, Duan S, Yi X, Yao J, Zhou S, Wei Z, et al. On the essence and prospect: an investigation of alignment approaches for big models. arXiv:240304204; 2024.

[196]

Barceló R, Alcázar C, Tobar F. Avoiding mode collapse in diffusion models fine-tuned with reinforcement learning. 2024. arXiv:241008315.

[197]

Asperti A, George F, Marras T, Stricescu RC, Zanotti F. A critical assessment of modern generative models’ ability to replicate artistic styles. Big Data Cogn Comput 2025; 9(9):231.

[198]

Qiang D, Ye Y, Zhang L. Computational urban design:an exploration of new urban science. In: Proceedings of the ACSA 110th annual meeting—EMPOWER, 2022 May 18-20, online. Washington, DC: Association of Collegiate Schools of Architecture (ACSA); 2022. p. 171-8.