[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85627-en":3,"doc-seo-85627-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85627,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Rethinking the UI of GenUI: A Tale of Two Designs","GenUI is an emerging class of AI tools that generate UI mock-ups from users’ high-level descriptions, aiming to broaden access to UX design exploration. Current GenUI workflows often mirror conversational LMs by using unstructured prompts and a depth-first strategy that quickly yields high-fidelity prototypes. This work examines whether such unstructured, depth-first, high-fidelity design supports crucial early “0-to-1” ideation. A contrastive structured, breadth-first, low-fidelity approach is evaluated via a study with 24 UX designers and product managers, revealing benefits and trade-offs.","RETHINKING THE UI OF GENUI: A TALE OF TWO DESIGNS  \nA PREPRINT  \nXiang ‘Anthony’ Chen*  \nHCI Research, UCLA Los Angeles, California, United States  \nSavvas Dimitrios Petridis  \nGoogle DeepMind New York, New York, United States  \nTian Deng  \nCloud AI, Google Mountain View, California, United States  \nHumad Bari  \nHCI Research, UCLA Los Angeles, California, United States  \narXiv :2606 . 13843v2 [ cs .HC] 11 Jul 2026  \nRuofei Du  \nGoogle XR San Francisco, California, United States  \nYang Li  \nGoogle DeepMind Mountain View, California, United States  \nJuly 14, 2026  \nABSTRACT  \nGenUI is an emergent class of AI tools that use large models (LM) to generate UI mock-ups based on users’ high-level descriptions, promising to democratize UX design exploration for broader audience.  \nMost GenUI designs to-date tend to inherit the conventions of conversational LMs (e.g., ChatGPT and Gemini), where a user describes their design needs primarily via an unstructured prompt, and the tool then takes a depth-first approach, delving into the design right away and producing a high fidelity prototype. In this research, we rethink how well this unstructured, depth-first, and highfidelity GenUI design can support the important early-stage, 0-to-1 design exploration. To probe this question, we propose a contrastive design with structured input, breadth-first exploration, and low-fidelity generation. We then conducted a comparison study with 24 UX designers and product managers who conducted mini design exploration exercises using an existing and our contrastive GenUI tools. Findings reveal participants’ perceived benefits and trade-offs of the two GenUI designs: (i) Structured input surfaces key facets but requires more work, raising entry barriers to start exploration; (ii) Breadth-first workflow reveals more possibilities, but previewing UX ideas spanning many screens remains hard; and (iii) Though low fidelity has value, professionals favor high fidelity—it fits practice, and GenAI heightens fidelity expectations. We conclude with design implications for GenUI and similar AI-powered creativity support tools.  \nKeywords GenUI · UX Design · Generative AI · Design Tools  \n1 Introduction  \nPre-trained large models can now enable Generative User Interfaces (GenUI)—generating UI screen mockups from high-level inputs (e.g., a textual description), promising to democratize UX design exploration for broader audience. One major promise of GenUI is supporting the important early-stage,“0-to-1”2 ideation Chen et al. (2025), which often  \n∗ Corresponding author: [xac@ucla.edu](xac@ucla.edu)  \n2There are two distinct types of design needs that GenUI tools can support: “0-to-1” vs.“n-to-(n+1)”, where the former is about exploring a new feature or product from scratch and the latter is about adding or changing features on an existing product.  \nStudy Findings of Comparing Two GenUI Designs  \nDepth-vs. Breadth-First Workflow  \nBreadth-first workflow reveals more possibilities, but previewing UX ideas containing many screens remains hard.  \nHigh-vs. Low-Fidelity Mockups  \nThough low-fi has value, professionals favor hi-fi—it fits practice, and GenAI heightens fidelity expectations.  \nImplications for Design  \nHybrid, unstructured-to-structured input  \n Mixed-initiatively   \nUnstructured text Structured fields  \nPreview UX designs for agile exploration  \nCreate one design first, then extrapolate  \nCompare alternatives side-by-side  \nRapid serial visual presentation of UI  \nGenerate mixed-fidelity UI mockups  \nGlobally or locally adjust fidelity on selected attributes  \nFigure 1: We conducted a study to understand two contrastive designs of GenUI—tools that employ large models to generate UI mockups: (i) Input: a conventional open-ended, unstructured prompt vs. a structured form that guides users to provide key information; (ii) Workflow: delving into a design right away (depth-first) vs. starting with exploring a design space (breadth-first); (iii) Output: generating ","cbCaid654DJIT31R","https://ap.wps.com/l/cbCaid654DJIT31R","pdf",3418500,1,27,"English","en",105,"# Introduction\n## Depth-vs. Breadth-First Workflow\n## High-vs. Low-Fidelity Mockups\n## Implications for Design","[{\"question\":\"What problem does GenUI aim to solve in UX design exploration?\",\"answer\":\"GenUI uses large language models to generate UI mock-ups from high-level descriptions, with the goal of democratizing early UX design exploration for a broader audience.\"},{\"question\":\"How does the paper compare two GenUI interaction designs?\",\"answer\":\"It contrasts unstructured, depth-first input that quickly produces high-fidelity prototypes with structured input, breadth-first exploration, and low-fidelity generation.\"},{\"question\":\"What trade-offs did participants report between the two designs?\",\"answer\":\"Structured input surfaces key facets but increases work before exploration; breadth-first workflows reveal more possibilities yet make multi-screen preview harder; low fidelity is still valuable, but professionals preferred high fidelity due to practice fit and heightened expectations from generative AI.\"}]",1784205039,68,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"rethinking-the-ui-of-genui-a-tale-of-two-designs","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/rethinking-the-ui-of-genui-a-tale-of-two-designs/85627/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does GenUI aim to solve in UX design exploration?","Question",{"text":75,"@type":76},"GenUI uses large language models to generate UI mock-ups from high-level descriptions, with the goal of democratizing early UX design exploration for a broader audience.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the paper compare two GenUI interaction designs?",{"text":80,"@type":76},"It contrasts unstructured, depth-first input that quickly produces high-fidelity prototypes with structured input, breadth-first exploration, and low-fidelity generation.",{"name":82,"@type":73,"acceptedAnswer":83},"What trade-offs did participants report between the two designs?",{"text":84,"@type":76},"Structured input surfaces key facets but increases work before exploration; breadth-first workflows reveal more possibilities yet make multi-screen preview harder; low fidelity is still valuable, but professionals preferred high fidelity due to practice fit and heightened expectations from generative AI.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]