[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85957-en":3,"doc-seo-85957-105":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},85957,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","AI YOU Town Make Friends and Money with Your Digital Twin","Existing methods for inferring user traits and generating persona-consistent replies often depend on static prompting. They miss calibrated uncertainty, disregard sequential conversational evidence, and degrade during long interactions. AI YOU introduces a framework that continually updates a 22-dimension personality profile from dialogue and embodies it in a personal digital twin. It integrates prompting, Bayesian updating, and conformal prediction, supported by refreshed memory anchoring and three-layer cognitive memory to preserve persona consistency, improve uncertainty calibration, and reduce trait drift across long multi-agent role play.","AI YOU Town: Make Friends and Money with Your Digital Twin  \nYan Lin1,2 * , Yuyang Dai1 * , Jiahui Geng3 , Yuxia Wang1  \n1INSAIT, Sofia University “St. Kliment Ohridski”  \n2Newcastle University 3Linköping University  \n[y.lin64@ncl.ac.uk](y.lin64@ncl.ac.uk) , [y9657422@gmail.com](y9657422@gmail.com) , [jiahui.geng@liu.se](jiahui.geng@liu.se) , [yuxia.wang@insait.ai](yuxia.wang@insait.ai)  \narXiv :2607 . 10539v 1 [ cs .AI] 12 Jul 2026  \nAbstract  \nExisting approaches to infer user traits and generate responses consistent with a persona rely on static prompting. They lack calibrated uncertainty, ignore sequential evidence, and drift during long interactions. We present AI YOU, a framework that continually updates a personality profile with 22 dimensions from conversation and embodies it in a personal digital twin. Practically, the system combines prompting, Bayesian updating, and conformal prediction for persona inference. A periodically refreshed memory anchor and cognitive memory with three layers preserve persona consistency overlong interactions. Across the main results, AI YOU (i) achieves conformal coverage ranging from 0.921 to 0.976,(ii) improves uncertainty calibration and reasoning grounded in memory, and (iii) enhances persona fidelity over static prompting in role playing over 100 turns while reducing trait drift, for most evaluated backbones under adversarial settings with multiple agents. The prototype AI YOU Town initializes an imaginative twin world for future interaction. The online demo is available at [quinnnnnne-ai-you.hf.space](quinnnnnne-ai-you.hf.space).  \n1 Introduction  \nImagine a virtual town populated by personal digital twins that interact, socialize, and work on behalf of their users while preserving users’ personalities. Large Language Models (LLMs) have shown promising ability to infer personality traits from text and generate dialogue that reflects individual communicative styles (Shao et al., 2023 ; Park et al., 2023 ; Peters et al., 2024 ; Jiang et al., 2024 ; Marengo et al., 2025), making such systems increasingly plausible. However, building a reliable personal digital twin requires solving three intertwined challenges that existing systems address only in isolation.  \n* Equal contribution.  \nFirst, personality inference from conversation requires uncertainty-aware estimation: single-pass LLM predictions produce point estimates without calibrated confidence (Song et al., 2023 ; Lin, 2025) . Second, personality evidence accumulates across turns, yet most pipelines treat utterances independently, lacking mechanisms for sequential belief updating (Tan et al., 2025 ; Chen et al., 2025) . Third, personality inference and persona-driven generation are typically treated as separate problems (Tseng et al., 2024 ; Zhong et al., 2025), creating a gap between understanding and embodying a user.  \nTherefore, we present AI YOU, an interactive multi-agent framework that organically unifies isolated modules in one system. Modules interact cohesively: personality inference outputs serve asthe input of persona modeling, persona-conditioned generations support persona updating, and a shared three-layer memory enables persona consistency and long-horizon reasoning. It is related to LLMbased personality simulation, dynamic persona inference, persona-conditioned generation, and digital-twin simulation. We provide a detailed related work in Section 2.  \nWe further prototype the AI YOU Town, a virtual environment where personal digital twins (PDTs) interact, socialize, and work. As illustrated in Figure 1, it is a bidirectional ecosystem that connects the real world and AI YOU Town. The story begins when a real user initiates a conversation with either a twin or another real user logged into the town. Then, a specialized agent continually estimates a 22-dimensional profile based on user conversations, where Bayesian posterior inference and conformal prediction maintain calibrated uncertainty. The inferred persona wou","cbCait0IKYXj665E","https://ap.wps.com/l/cbCait0IKYXj665E","pdf",1555089,3,1,28,"English","en",105,"# Introduction\n## Challenges in Persona Inference and Digital Twin Reliability\n## Proposed Framework: AI YOU\n# Related Work\n## LLM-Based Personality Simulation","[{\"question\":\"What problems does AI YOU address compared with static-prompting persona approaches?\",\"answer\":\"AI YOU targets three gaps: lack of calibrated uncertainty, treating each utterance independently without sequential belief updating, and separating personality inference from persona-conditioned generation.\"},{\"question\":\"How does AI YOU infer and update the user’s personality?\",\"answer\":\"It continually estimates a 22-dimensional personality profile from conversations using Bayesian posterior inference and conformal prediction to maintain calibrated uncertainty, then uses the inferred persona to stabilize or initialize the digital twin.\"},{\"question\":\"What mechanism helps keep persona consistency during long interactions?\",\"answer\":\"AI YOU designs a three-layer memory architecture (working, episodic, and semantic) plus a periodically refreshed memory anchor, grounding generation in accumulated history to reduce trait drift over long horizons.\"}]",1784207374,71,{"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},"ai-you-town-make-friends-and-money-with-your-digital-twin","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/ai-you-town-make-friends-and-money-with-your-digital-twin/85957/",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","2026-07-24","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 problems does AI YOU address compared with static-prompting persona approaches?","Question",{"text":75,"@type":76},"AI YOU targets three gaps: lack of calibrated uncertainty, treating each utterance independently without sequential belief updating, and separating personality inference from persona-conditioned generation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does AI YOU infer and update the user’s personality?",{"text":80,"@type":76},"It continually estimates a 22-dimensional personality profile from conversations using Bayesian posterior inference and conformal prediction to maintain calibrated uncertainty, then uses the inferred persona to stabilize or initialize the digital twin.",{"name":82,"@type":73,"acceptedAnswer":83},"What mechanism helps keep persona consistency during long interactions?",{"text":84,"@type":76},"AI YOU designs a three-layer memory architecture (working, episodic, and semantic) plus a periodically refreshed memory anchor, grounding generation in accumulated history to reduce trait drift over long horizons.","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},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"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":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]