{"id":3624,"date":"2026-05-20T15:24:36","date_gmt":"2026-05-20T20:24:36","guid":{"rendered":"https:\/\/wordpress.cs.vt.edu\/3digroup\/?p=3624"},"modified":"2026-05-20T15:24:37","modified_gmt":"2026-05-20T20:24:37","slug":"evaluating-the-use-of-conversational-agents-for-immersive-collaboration","status":"publish","type":"post","link":"https:\/\/wordpress.cs.vt.edu\/3digroup\/2026\/05\/20\/evaluating-the-use-of-conversational-agents-for-immersive-collaboration\/","title":{"rendered":"Evaluating the Use of Conversational Agents for Immersive Collaboration"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">Collaborative Virtual Environments (CVEs) empower geographically dispersed teams to work across time and physical space within a shared virtual workplace. Within CVEs, team members can communicate in real-time and preserve information about their work through text annotations. However, collaborators may not always be available to assist with tasks or answer questions regarding prior contributions in the CVE. Conversational agents powered by large language models (LLMs) have the potential to address these gaps in availability and knowledge by leveraging annotations and recorded actions within the CVE to answer users&#8217; questions. However, the effectiveness of agent-mediated assistance relative to a live human collaborator remains underexplored. To address this gap, we conducted an extended reality (XR) study examining differences in task performance and user experience during immersive information-seeking collaboration. Our findings indicate that collaborating with a conversational agent yields comparable task performance and satisfaction, but with trade-offs in prompting behavior, trust, and enjoyment.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"942\" height=\"375\" src=\"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-content\/uploads\/sites\/141\/2026\/05\/CA__Teaser.png\" alt=\"\" class=\"wp-image-3626\" srcset=\"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-content\/uploads\/sites\/141\/2026\/05\/CA__Teaser.png 942w, https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-content\/uploads\/sites\/141\/2026\/05\/CA__Teaser-300x119.png 300w, https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-content\/uploads\/sites\/141\/2026\/05\/CA__Teaser-768x306.png 768w\" sizes=\"auto, (max-width: 942px) 100vw, 942px\" \/><figcaption class=\"wp-element-caption\">Participant view of the video-see-through collaborative virtual environment showing the virtual inspection object and a portion of the paper audit form. <strong>A<\/strong>: Initial configuration with the object floating above the desk. <strong>B<\/strong>: The participant repositions the object using the controller to locate an annotation indicator (green sphere at the center of a cell). <strong>C<\/strong>: The participant reviews the annotation for the highlighted cell while recording information in the paper audit form.<\/figcaption><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Collaborative Virtual Environments (CVEs) empower geographically dispersed teams to work across time and physical space within a shared virtual workplace. Within CVEs, team members can communicate in real-time and preserve information about their work through text annotations. However, collaborators may not always be available to assist with tasks or answer questions regarding prior contributions in <a href=\"https:\/\/wordpress.cs.vt.edu\/3digroup\/2026\/05\/20\/evaluating-the-use-of-conversational-agents-for-immersive-collaboration\/\" class=\"more-link\">&#8230;<\/a><\/p>\n","protected":false},"author":383,"featured_media":3625,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[11],"tags":[27,453,552],"ppma_author":[479,502,511,539,521,400,540,391],"class_list":["post-3624","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-projects","tag-augmented-reality","tag-collaboration","tag-human-centered-ai"],"jetpack_featured_media_url":"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-content\/uploads\/sites\/141\/2026\/05\/CA__Annotation.png","authors":[{"term_id":479,"user_id":383,"is_guest":0,"slug":"agiovannelli","display_name":"Alexander Giovannelli","avatar_url":{"url":"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-content\/uploads\/sites\/141\/2022\/05\/IMG_6776-e1651771320966.jpg","url2x":"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-content\/uploads\/sites\/141\/2022\/05\/IMG_6776-e1651771320966.jpg"},"author_category":"1","user_url":"https:\/\/agiovannelli.github.io\/","last_name":"Giovannelli","first_name":"Alexander","job_title":"","description":"My expertise lies at the intersection of human-computer interaction, extended reality, and computer-supported cooperative work. I investigate how immersive environments can support effective remote and cross-temporal collaboration, with a growing focus on integrating AI assistance into collaborative XR workflows."},{"term_id":502,"user_id":394,"is_guest":0,"slug":"cconnor22","display_name":"Cherelle Connor","avatar_url":"https:\/\/secure.gravatar.com\/avatar\/812eb62a033c454fd7426cfc8e01d25ca21226e5c95ec5e0801899ad518aff52?s=96&d=mm&r=g","author_category":"","user_url":"","last_name":"Connor","first_name":"Cherelle","job_title":"","description":"I am a third-year Computer Science Ph.D. student at Virginia Tech. My current research focuses on the exploration of cognitive load reduction and cognitive flow support in Immersive Spaces to Think."},{"term_id":511,"user_id":0,"is_guest":1,"slug":"haichao-miao","display_name":"Haichao Miao","avatar_url":"https:\/\/secure.gravatar.com\/avatar\/?s=96&d=mm&r=g","author_category":"","user_url":"","last_name":"","first_name":"","job_title":"","description":""},{"term_id":539,"user_id":0,"is_guest":1,"slug":"vuthea-chheang","display_name":"Vuthea Chheang","avatar_url":"https:\/\/secure.gravatar.com\/avatar\/?s=96&d=mm&r=g","author_category":"","user_url":"","last_name":"","first_name":"","job_title":"","description":""},{"term_id":521,"user_id":0,"is_guest":1,"slug":"timo-bremer","display_name":"Timo Bremer","avatar_url":"https:\/\/secure.gravatar.com\/avatar\/?s=96&d=mm&r=g","author_category":"","user_url":"","last_name":"","first_name":"","job_title":"","description":""},{"term_id":400,"user_id":254,"is_guest":0,"slug":"sdavari","display_name":"Shakiba Davari","avatar_url":{"url":"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-content\/uploads\/sites\/141\/2020\/11\/sdavari.jpg","url2x":"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-content\/uploads\/sites\/141\/2020\/11\/sdavari.jpg"},"author_category":"","user_url":"","last_name":"Davari","first_name":"Shakiba","job_title":"","description":"With a background spanning human-computer interaction (HCI), applied machine learning (ML), and UX\/UI design, my work bridges AI and design, creating frameworks and principles to address real-world challenges and deliver meaningful user experiences.\r\nDuring my Ph.D., I focused on intelligent Augmented and eXtended Reality (AR\/XR) interfaces exploring ways to make AR more adaptive and user-centered. I developed context-aware AR solutions to enhance usability, efficiency, and social interaction while addressing AR challenges such as spatial layout, occlusion, and social intrusiveness in dynamic scenarios. My dissertation provides a roadmap for integrating AI with AR design and establishes frameworks and design principles for effective AR across various contexts."},{"term_id":540,"user_id":0,"is_guest":1,"slug":"brian-giera","display_name":"Brian Giera","avatar_url":"https:\/\/secure.gravatar.com\/avatar\/?s=96&d=mm&r=g","author_category":"","user_url":"","last_name":"","first_name":"","job_title":"","description":""},{"term_id":391,"user_id":331,"is_guest":0,"slug":"dbowman","display_name":"Doug Bowman","avatar_url":{"url":"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-content\/uploads\/sites\/141\/2021\/01\/professional_photo2_2019-cropped-square-smaller-scaled.jpg","url2x":"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-content\/uploads\/sites\/141\/2021\/01\/professional_photo2_2019-cropped-square-smaller-scaled.jpg"},"author_category":"1","user_url":"","last_name":"Bowman","first_name":"Doug","job_title":"","description":"Doug A. Bowman is the Frank J. Maher Professor of <a href=\"http:\/\/www.cs.vt.edu\">Computer Science<\/a> at <a href=\"http:\/\/www.vt.edu\">Virginia Tech<\/a>. He is the principal investigator of the <a href=\"http:\/\/wordpress.cs.vt.edu\/3digroup\/\">3D Interaction Group<\/a>, focusing on the topics of three-dimensional user interfaces, VR\/AR user experience, and the benefits of immersion in virtual environments.\r\n\r\nDr. Bowman is one of the co-authors of <a href=\"https:\/\/www.pearson.com\/us\/higher-education\/program\/La-Viola-3-D-User-Interfaces-Theory-and-Practice-2nd-Edition\/PGM101825.html\">3D User Interfaces: Theory and Practice<\/a>. He has served in many roles for the <a href=\"http:\/\/ieeevr.org\">IEEE Virtual Reality Conference<\/a>, including program chair, general chair, and steering committee chair. He also co-founded the IEEE Symposium on 3D User Interfaces (now part of IEEE VR). He received a CAREER award from the National Science Foundation for his work on 3D Interaction, and has been named an ACM Distinguished Scientist. He received the Technical Achievement award from the IEEE Visualization and Graphics Technical Committee in 2014 and the Career Impact Award from IEEE ISMAR in 2021.\r\n\r\nHis undergraduate degree in mathematics and computer science is from Emory University, and he received his M.S. and Ph.D. in computer science from the Georgia Institute of Technology.\r\n\r\n<a href=\"http:\/\/people.cs.vt.edu\/~bowman\/cv.pdf\">Curriculum vitae (PDF)<\/a>"}],"_links":{"self":[{"href":"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-json\/wp\/v2\/posts\/3624","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-json\/wp\/v2\/users\/383"}],"replies":[{"embeddable":true,"href":"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-json\/wp\/v2\/comments?post=3624"}],"version-history":[{"count":1,"href":"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-json\/wp\/v2\/posts\/3624\/revisions"}],"predecessor-version":[{"id":3627,"href":"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-json\/wp\/v2\/posts\/3624\/revisions\/3627"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-json\/wp\/v2\/media\/3625"}],"wp:attachment":[{"href":"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-json\/wp\/v2\/media?parent=3624"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-json\/wp\/v2\/categories?post=3624"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-json\/wp\/v2\/tags?post=3624"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/wordpress.cs.vt.edu\/3digroup\/wp-json\/wp\/v2\/ppma_author?post=3624"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}