[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81592-en":3,"doc-seo-81592-105":30,"detail-sidebar-cat-0-en-105":83},{"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},81592,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","Knowledge-Based Design Requirements for Generative Social Robots in Higher Education","Generative social robots (GSRs) driven by large language models offer adaptive, conversational tutoring, yet they introduce risks including misinformation, overreliance, and privacy violations. Existing responsible-AI and educational-technology frameworks emphasize desired behaviors but rarely define the knowledge prerequisites needed for reliable generative tutoring. Through twelve semistructured interviews with university students and lecturers, the work extracts twelve design requirements organized into self-knowledge, user-knowledge, and context-knowledge, enabling responsible and effective higher-education tutoring.","arXiv :2602 . 12873v 5 [ cs .HC] 9 Jul 2026  \nKnowledge-Based Design Requirements for Generative Social Robots in Higher Education  \nS. Vonschallen 1 ,2 ,3[0009−0001−4262−938X], D. Oberle 1[0009−0008−9375−6398],  \nT. Schmiedel 1⋆[0000−0003−3837−7615], and F. Eyssel3[0000−0002−4978−8922]  \n1 Zurich University of Applied Sciences, 8400 Winterthur, Switzerland  \n2 University of Applied Sciences and Arts Northwestern Switzerland, 4052 Basel, Switzerland  \n3 Bielefeld University, 33615 Bielefeld, Germany  \nAbstract. Generative social robots (GSRs) powered by large language models enable adaptive, conversational tutoring but also introduce risks such as misinformation, overreliance, and privacy violations. Existing frameworks for educational technologies and responsible AI primarily define desired behaviors, yet they rarely specify the knowledge prerequisites that enable generative agents to express these behaviors reliably.  \nTo address this gap, we adopt a knowledge-based design perspective and investigate what information tutoring-oriented GSRs require to function responsibly and effectively in higher education. Based on twelve semistructured interviews with university students and lecturers, we identified twelve design requirements across three knowledge types: self-knowledge (assertive, conscientious, and friendly personality with customizable role), user-knowledge (personalized information about student learning goals, learning progress, motivation type, emotional state, and background), and context-knowledge (learning materials, educational strategies, courserelated information, and physical learning environment) . Drawing from these results, this work provides a structured foundation for the design of tutoring GSRs, aligning generative AI capabilities with pedagogical and ethical expectations.  \nKeywords: Responsible Design · Social Robots · Education · Generative AI · Large Language Models  \n1 Introduction  \nAs universities strive to support students in increasingly complex learning environments, students differ substantially in what they bring to the classroom. Variations in students’ prior knowledge, skills, experiences, and learning approaches have led to growing expectations for individualized feedback and support [42] . However, large class sizes and limited instructor availability make sustained one-on-one  \ntutoring difficult to provide at scale [66] . Study groups provide a compelling alternative that supports deeper understanding and sustained learning motivation ⋆ T. Schmiedel and F. Eyssel share senior authorship.  \n2 S. Vonschallen et al.  \n[34, 52], but their effectiveness depends on availability, peer expertise, and group dynamics [10, 40] . Social robots represent a promising approach to complement existing learning support by offering readily available, interactive guidance, study companionship, and encouragement for productive learning behaviors [8, 32] . These tasks require nuanced communication skills – such as giving personalized feedback to increase learning effectiveness [1, 17, 24] or providing emotional support to promote learner motivation [15, 16, 28] .  \nIn the past, social robots were limited by pre-scripted dialogue and constrained interaction flexibility [30] . This made deployment in educational settings challenging, given that students have diverse academic needs [54, 62] . More recently, human–robot interaction has advanced through generative AI, particularly Large Language Models (LLMs) [7, 11, 30] . Generative Social Robots (GSRs) use generative AI models such as LLMs to autonomously produce and coordinate verbal and non-verbal communicative behavior in a natural and adaptive manner [57, 56] . Thus, GSRs differ from rule-based social robots with fixed interaction logic, and from AI-based tutoring systems without embodied social presence and multimodal interaction. This enables GSRs to provide personalized and context-sensitive tutoring [1, 48, 55, 54] . In doing so, GSRs may improve learni","cbCaicJd6eHsyAHL","https://ap.wps.com/l/cbCaicJd6eHsyAHL","pdf",764604,2,1,20,"English","en",105,"# 1 Introduction\n# 2 Related Work\n# Knowledge-Based Design Requirements for GSRs in Higher Education","[{\"question\":\"What risks motivate the responsible-design focus of tutoring GSRs?\",\"answer\":\"The paper highlights risks such as confidently produced inaccuracies, learner overreliance that undermines autonomy, unfair or biased feedback, and privacy violations when processing sensitive student data.\"}]",1784174572,50,{"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":78,"head_meta":80,"extra_data":82,"updated_unix":28},"knowledge-based-design-requirements-for-generative-social-robots-in-higher-education","",{"@graph":36,"@context":77},[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/knowledge-based-design-requirements-for-generative-social-robots-in-higher-education/81592/",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","2026-07-22","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"What risks motivate the responsible-design focus of tutoring GSRs?","Question",{"text":75,"@type":76},"The paper highlights risks such as confidently produced inaccuracies, learner overreliance that undermines autonomy, unfair or biased feedback, and privacy violations when processing sensitive student data.","Answer","https://schema.org",{"og:url":51,"og:type":79,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":81,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":84},[85,89,93,97,102,106,111,114,118,121,125],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":29,"slug":105},6,"Technology","technology",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":22,"slug":117},9,"Religion & Spirituality","religion-spirituality",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":119,"show_sort_weight":22,"slug":120},"World Cup","world-cup",{"id":122,"doc_module":4,"doc_module_name":46,"category_name":123,"show_sort_weight":122,"slug":124},10,"Lifestyle","lifestyle",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":98,"slug":128},19,"General","general"]