[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83257-en":3,"doc-seo-83257-105":30,"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},83257,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","Creativity from Friction: Human–AI Interaction for Exploratory Structural Design","AI agents that deliver final answers from user prompts often fail to support creative practice. Structural design and architecture require interactive systems that help designers externalise ideas, compare alternatives, and iteratively refine partial solutions. Because structural outputs must satisfy constraints on geometry, mechanical behavior, materials, and cost, friction can both hinder and spark creativity. This paper proposes constrained human–AI co-creation using vision-language models to make exploration conversational, multimodal, and responsive to evolving intent.","Creativity from Friction:  \nHuman–AI Interaction for Exploratory Structural Design  \nRicardo Maia Avelino 1 2 Rita Sevastjanova 2 Tom Van Mele 1 Philippe Block 1 Mennatallah El-Assady 2  \narXiv :2607 .0752 1v 1 [ cs .HC] 8 Jul 2026  \nAbstract  \nAI agents that generate final answers based on user input often do not meet the needs of creative fields. Fields such as structural design and architecture need interactive systems that help users externalise and develop ideas, explore alternatives, and refine partial solutions. The final product of such designs needs to comply with many constraints concerning, e.g., spatial configuration, mechanical behaviour, material quantities, and costs. These constraints create friction in the design process, which can stimulate novel and creative solutions. In this paper, we discuss themisalignment between current generative AI goals to remove friction and provide final solutions and the needs of creators, such as structural designers, who develop ideas through iterative work. We present the design dimensions of systems allowing for constrained human–AI co-creation that rely on vision-language models making structural exploration conversational, multimodal, and responsive to evolving human intent in ways that follow and augment the discipline’s creative process. Through a pilot design interface based on these principles and a study with experts in the field, this paper shows how structural designers perceive interactive AI systems and how such systems can support design space exploration by reducing repetitive modelling friction while preserving reflective design friction.  \n1. Introduction  \nGenerative AI is often evaluated for its ability to produce plausible final outputs such as an image, a text, a plan, ora model from  user input. However, creative design work  \n1Block Research Group, Department of Architecture, ETH Zurich, Switzerland 2IVIA Lab, Department of Computer Science, ETH Zurich, Switzerland. Correspondence to: Ricardo Maia Avelino \u003C[mricardo@ethz.ch](mricardo@ethz.ch) > .  \nICML’26 Workshop on Human-AI Co-Creativity, Seoul, South Korea. Copyright 2026 by the author(s) .  \nrarely progresses as a one-shot process to the final product. Designers externalise partial ideas, compare alternatives, and use intermediate models to think, collaborate, and create. This view resonates with Schn’s model for professionals of creative disciplines that engage in “reflection-in-action”adapting their creation process to ever evolving constraints and ideas (Schn, 1983) . Thus, generative AI in creative domains must shift from workflow automation to exploration augmentation (Rezwana & Maher, 2023 ; Wang et al., 2025) .  \nStructural design makes this need particularly visible. It is a creative discipline, but not an unconstrained one. Structural engineers must balance spatial constraints while reasoning about loads, supports, spans, constructability, economy, safety, among others. In doing so, engineers seek creative solutions that emerge from the friction of managing all these constraints. Teng et al. (2004) define creativity in structural design as the production of a design that is novel and satisfies functional constraints, and highlight the importance of divergent thinking to draw analogies from solutions to previous problems and explore different alternatives.  \nStructural exploration has been the focus of recent research in which algorithms that explore different structural forms are preferred rather than single-objective optimisations on predetermined typologies (Mueller, 2014 ; Danhaive & Mueller, 2021 ; Lee et al., 2016 ; Saldana Ochoa et al., 2021) . Generative AI brings new opportunities to expand this exploration by allowing multimodal interactions and advanced reasoning (Zhang et al., 2025 ; Suh et al., 2024) . This raises a key question: how can we formally define such interactions so that these systems effectively support and enhance the design process?  \nWe answer this question by intr","cbCairc3Q0Ju9Ki9","https://ap.wps.com/l/cbCairc3Q0Ju9Ki9","pdf",5885143,2,1,12,"English","en",105,"# Introduction\n# Structural Design Exploration and Human–AI Co-Creation\n## Structural Design as Creative Constraint Negotiation","[{\"question\":\"Why is standard “final-answer” generative AI insufficient for structural design?\",\"answer\":\"Structural design is an iterative process where designers externalise partial ideas, compare alternatives, and refine constraints. Final-answer automation does not support this reflective, evolving workflow.\"},{\"question\":\"How does the paper frame “friction” in creative structural design?\",\"answer\":\"The paper distinguishes productive friction that arises from negotiating domain constraints from friction that comes from repetitive, mechanical actions. Productive friction can stimulate novel solutions while repetitive friction can be reduced.\"},{\"question\":\"What is the proposed approach for human–AI co-creation in structural exploration?\",\"answer\":\"The paper introduces constrained co-creation workflows where ongoing negotiation of structural constraints shapes exploration. It presents a prototype interface and evaluates how experts use it for design-space exploration.\"}]",1784186317,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"creativity-from-friction-humanai-interaction-for-exploratory-structural-design","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/creativity-from-friction-humanai-interaction-for-exploratory-structural-design/83257/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","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},"Why is standard “final-answer” generative AI insufficient for structural design?","Question",{"text":75,"@type":76},"Structural design is an iterative process where designers externalise partial ideas, compare alternatives, and refine constraints. Final-answer automation does not support this reflective, evolving workflow.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the paper frame “friction” in creative structural design?",{"text":80,"@type":76},"The paper distinguishes productive friction that arises from negotiating domain constraints from friction that comes from repetitive, mechanical actions. Productive friction can stimulate novel solutions while repetitive friction can be reduced.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the proposed approach for human–AI co-creation in structural exploration?",{"text":84,"@type":76},"The paper introduces constrained co-creation workflows where ongoing negotiation of structural constraints shapes exploration. It presents a prototype interface and evaluates how experts use it for design-space exploration.","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":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]