[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85061-en":3,"doc-seo-85061-105":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},85061,1099514067415,"Rowan","https://ap-avatar.wpscdn.com/avatar/100002539d78ffe74a7?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779092875211072502",8,"Research & Report","Simulating the Resident Generating Executable Smart Home Schedules via LLM Personas","Smart homes are a key domain for HCI research, including work on usable security and privacy, where studies ideally rely on datasets from real homes. Real-world data collection is slow, costly, and privacy-sensitive because it requires prolonged observation in highly private environments. The paper proposes using LLMs to generate diverse resident personas that interact with a simulated smart home, yielding behaviorally grounded, structured interaction schedules that can be executed on physical testbeds. It introduces a design framework, a multi-stage LLM pipeline, and a feasibility proof of concept.","Simulating the Resident: Generating Executable Smart Home  \nSchedules via LLM Personas  \nVictor Jüttner Erik Buchmann  \n[victor.juettner@uni-leipzig.de](victor.juettner@uni-leipzig.de)[ ](victor.juettner@uni-leipzig.de)[erik.buchmann@uni-leipzig.de](erik.buchmann@uni-leipzig.de)[ ](erik.buchmann@uni-leipzig.de)ScaDS.AI Dresden/Leipzig, Leipzig University Leipzig, Germany  \nXenia Wagner Christoph Jahn  \n[xenia.wagner@rohde-schwarz.com](xenia.wagner@rohde-schwarz.com)[ ](xenia.wagner@rohde-schwarz.com)[christoph.jahn@rohde-schwarz.com](christoph.jahn@rohde-schwarz.com)[ ](christoph.jahn@rohde-schwarz.com)[ipoque GmbH](ipoque GmbH), [a Rohde & Schwarz company](a Rohde & Schwarz company)[ ](a Rohde & Schwarz company)Leipzig, Germany  \narXiv :2607 .0823 1v 1 [ cs .CR] 9 Jul 2026  \nAbstract  \nSmart homes have emerged as an important domain for HCI research, including work on usable security and privacy. Ideally, studies in these areas draw on datasets collected in real homes with real residents, capturing authentic device interactions, network traffic, and daily routines. However, creating such datasets is slow, expensive, and raises significant privacy concerns, as it requires long-term observation of people in their most private spaces. We propose using LLMs to generate diverse resident personas that interact with a simulated smart home, producing behaviorally grounded interaction schedules that can be executed on physical testbeds. We present (1) a design framework configuring simulated households across five socio-technical dimensions,(2) a multi-stage LLM pipeline that produces structured, executable device interaction schedules, and (3) a proof of concept demonstrating feasibility. Asa work in progress, we aim to support scalable, privacy-conscious smart-home experimentation without relying on intrusive realworld data collection.  \nKeywords  \nSmart Home, LLM, Personas, HCI, IoT Testbed  \n1 Introduction  \nSmart homes are becoming an integral part of everyday domestic life, with the number of connected households growing rapidly worldwide [7] . Smart devices such as lights, thermostats, and speakers generate continuous traces of how residents live, move, and automate their daily routines [5, 20], making smart homes an increasingly important setting for HCI research. Behavioral traces from smart devices are relevant for designing usable, context-aware systems, but also carry significant implications for privacy and security: Observable device traffic can reveal fine-grained information about residents’ habits and daily behavior [1, 3, 17] .  \nHowever, studying realistic smart-home behavior constitutes a methodological challenge. Researchers need data about how people actually interact with devices in everyday life in order to design and evaluate secure and privacy-aware systems, automation logic, and user experiences. Yet collecting such data in real households often requires long-term and invasive observation, creating a tension between the need for ecologically valid data and protecting residents’ privacy.  \nAI-HCD 2026: 1st Symposium on Artificial Intelligence throughout the Human-Centered Design Process, HTWD – University of Applied Sciences, 01069 Dresden, Germany.  \n© 2026 Copyright held by the owner/author(s), DOI: [https://doi.org/10.18420/AIHCD2026_025](https://doi.org/10.18420/AIHCD2026_025) . Except as otherwise noted, this paper is licenced under the Creative Commons Attribution 4.0 International Licence. To view a copy of this licence, visit [http://creativecommons.org/licenses/by/4.0](http://creativecommons.org/licenses/by/4.0) .  \nReal smart-home datasets [2, 5, 14] are expensive to collect, limited to a small number of homes, and do not easily generalize across diverse household compositions, device ecosystems, or usage patterns. One way to bypass these limitations is to simulate household behavior synthetically. Large language models (LLMs) offera promising approach: They have recently demonstrated strong potenti","cbCaivEFmy9YQFoR","https://ap.wps.com/l/cbCaivEFmy9YQFoR","pdf",642750,2,1,5,"English","en",105,"# Introduction\n## Motivation and challenge\n## Proposed approach\n## Research question and contributions","[{\"question\":\"Why are real smart-home datasets difficult to use for HCI research?\",\"answer\":\"They are expensive and typically limited to a small number of homes, and they often require long-term, invasive observation that raises major privacy concerns.\"},{\"question\":\"What is the core idea of the proposed method?\",\"answer\":\"Use LLMs to generate diverse resident personas and simulated daily routines, then transform them into executable smart-home interaction schedules for physical testbeds.\"},{\"question\":\"What components does the paper claim as contributions?\",\"answer\":\"A design framework using five socio-technical dimensions, a multi-stage LLM pipeline that produces structured executable schedules, and a proof-of-concept demonstrating feasibility with coherent, persona-consistent traces.\"}]",1784200723,13,{"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},"simulating-the-resident-generating-executable-smart-home-schedules-via-llm-personas","",{"@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/simulating-the-resident-generating-executable-smart-home-schedules-via-llm-personas/85061/",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","2026-07-23","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 are real smart-home datasets difficult to use for HCI research?","Question",{"text":75,"@type":76},"They are expensive and typically limited to a small number of homes, and they often require long-term, invasive observation that raises major privacy concerns.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the core idea of the proposed method?",{"text":80,"@type":76},"Use LLMs to generate diverse resident personas and simulated daily routines, then transform them into executable smart-home interaction schedules for physical testbeds.",{"name":82,"@type":73,"acceptedAnswer":83},"What components does the paper claim as contributions?",{"text":84,"@type":76},"A design framework using five socio-technical dimensions, a multi-stage LLM pipeline that produces structured executable schedules, and a proof-of-concept demonstrating feasibility with coherent, persona-consistent traces.","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},[93,97,101,105,109,114,119,122,127,130,134],{"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":22,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"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":22,"slug":137},19,"General","general"]