[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82630-en":3,"doc-seo-82630-105":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},82630,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","OrchestrXR: A Multi-Agent System for Idea-to-Prototype XR Study Authoring","Extended Reality (XR) supports research on interaction, perception, and user behavior in immersive environments, where studies combine experimental tasks, 3D scenes, and interactive logic. Converting an initial XR study idea into a runnable Unity prototype is fragmented across study design, scene construction, and interaction implementation. OrchestrXR introduces a multi-agent human–AI workflow that preserves research intent across stages using structured schemas, agent orchestration, and interactive human-agent interfaces. A study with 12 XR researchers indicates strong intent preservation and effective early-stage authoring support.","arXiv :2607 .0 1588v 1 [ cs .HC] 2 Jul 2026  \nOrchestrXR: A Multi-Agent System for Idea-to-Prototype  \nXR Study Authoring  \nShuqi Liao  \nPurdue University West Lafayette, Indiana, USA  \nKarthik Ramani  \nPurdue University West Lafayette, Indiana, USA  \nChenfei Zhu  \nPurdue University West Lafayette, Indiana, USA  \nVoicu Popescu  \nPurdue University West Lafayette, Indiana, USA  \nFigure 1: OrchestrXR structures XR study authoring into three connected agent stages:  Study Design (SD),  Scene Generation (SG), and  Interaction Generation (IG). Users interact with the system through a shared  chat interface, while  Unity serves as the execution environment. Starting from an XR study idea, the system progressively translates research intent into structured study, scene, and interaction specifications, and ultimately an executable XR prototype in Unity.  \nAbstract  \nExtended Reality (XR) has become an important interaction paradigm in Human-Computer Interaction (HCI) . XR studies are used to investigate interaction, perception, and user behavior in immersive environments, and typically involve experimental tasks, 3D scenes, and interactive logic. However, turning an initial XR study idea into a runnable prototype remains fragmented across study design, scene construction, and interaction implementation. We present OrchestrXR, a multi-agent human–AI workflow for early-stage ideato-prototype XR study authoring. Rather than treating XR study creation as one-shot generation, OrchestrXR supports a controllable workflow across study design, scene generation, and interaction generation through structured schemas, multi-agent orchestration, and interactive human-agent interfaces, producing a Unity-based prototype from a researcher’s idea. A user study with 12 XR researchers suggests that OrchestrXR provides effective support for early-stage XR study authoring with strong intent preservation across stages.  \nCCS Concepts  \n• Human-centered computing → Interactive systems and tools; Virtual reality; • Computing methodologies → Intelligent agents.  \nKeywords  \nmulti-agent systems, large language models, authoring tools, extended reality, human-AI collaboration  \n1 Introduction  \nExtended Reality (XR) has become an important interaction paradigm in Human-Computer Interaction (HCI) [46, 57] . XR studies are commonly used to investigate interaction, perception, and user behavior in immersive environments, and typically involve experimental tasks, 3D scenes, and interactive logic [50, 54] . However, turning an initial XR study idea into a runnable prototype remains difficult [2, 32] . Authoring such prototypes requires researchers to move across disconnected layers of work, from specifying study goals and procedures, to constructing 3D scenes, to implementing  \ninteractive behavior in engines such as Unity [61] or Unreal Engine [16] . Because this process is also inherently iterative, pilot findings often force revisions across all three layers. As a result, early-stage XR prototyping remains fragmented, leaving a substantial gap between research ideas and executable artifacts.  \nRecent advances in Large Language Models (LLMs) have created new opportunities for complex authoring workflows, especially through multi-agent systems that can coordinate specialized roles and intermediate artifacts. Prior work has begun to explore LLMs and multi-agent systems for automating scientific workflows [21, 55, 65] . However, most existing approaches primarily operate on text or 2D artifacts [12, 53, 66, 70] . XR study authoring, by contrast, requires researchers to bridge multiple representations from abstract study design to spatial scene specification and executable interaction logic. This gap suggests an opportunity to leverage LLM-based agentic support for XR study authoring, helping accelerate early-stage XR research by reducing low-level implementation burden and enabling researchers to focus on higher-level idea creation.  \nTo ground XR study authoring supp","cbCaioeWYumn45bL","https://ap.wps.com/l/cbCaioeWYumn45bL","pdf",8004500,1,22,"English","en",105,"# Introduction\n## Problem: fragmented XR study prototyping\n## Opportunity: LLM-based multi-agent workflows\n## Formative findings and design strategies\n## OrchestrXR approach\n## Evaluation via user study","[{\"question\":\"What problem does OrchestrXR address in XR study authoring?\",\"answer\":\"It targets the fragmented process of turning an initial XR study idea into a runnable prototype, which spans study design, 3D scene construction, and interaction implementation.\"},{\"question\":\"How does OrchestrXR structure the workflow?\",\"answer\":\"It organizes XR study authoring into three connected agent stages: Study Design (SD), Scene Generation (SG), and Interaction Generation (IG), producing Unity-executable prototypes.\"},{\"question\":\"How is OrchestrXR evaluated and what are the main findings?\",\"answer\":\"A user study with 12 XR researchers used assigned task cases and open-ended exploration. Results indicate effective transformation into inspectable artifacts, strong preservation of study intent across stages, and a coherent idea-to-prototype workflow.\"}]",1784181915,55,{"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},"orchestrxr-a-multi-agent-system-for-idea-to-prototype-xr-study-authoring","",{"@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/orchestrxr-a-multi-agent-system-for-idea-to-prototype-xr-study-authoring/82630/",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 OrchestrXR address in XR study authoring?","Question",{"text":75,"@type":76},"It targets the fragmented process of turning an initial XR study idea into a runnable prototype, which spans study design, 3D scene construction, and interaction implementation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does OrchestrXR structure the workflow?",{"text":80,"@type":76},"It organizes XR study authoring into three connected agent stages: Study Design (SD), Scene Generation (SG), and Interaction Generation (IG), producing Unity-executable prototypes.",{"name":82,"@type":73,"acceptedAnswer":83},"How is OrchestrXR evaluated and what are the main findings?",{"text":84,"@type":76},"A user study with 12 XR researchers used assigned task cases and open-ended exploration. Results indicate effective transformation into inspectable artifacts, strong preservation of study intent across stages, and a coherent idea-to-prototype workflow.","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"]