[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85438-en":3,"doc-seo-85438-105":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},85438,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1782698725881665579",8,"Research & Report","InqEduAgent Adaptive AI Learning Partners with Gaussian Process Augmentation","Collaborative learning partnerships are vital to inquiry-based education, yet most current learning partners are assigned via experience-driven heuristics or rule-based assistants, limiting knowledge expansion and adaptability. InqEduAgent introduces an LLM-empowered generative agent framework that simulates and selects adaptive learning partners for inquiry learning. A Gaussian process–augmented matching mechanism models learner cognitive and evaluative traits, enabling partner selection from prior knowledge patterns. Experiments show consistently superior performance across learning scenarios and LLM configurations, advancing human–AI collaborative learning and personalized recommendation in web-based education.","InqEduAgent: Adaptive AI Learning Partners with Gaussian Process Augmentation  \nWen-Xi Yang 1 , Tian-Fang Zhao 1,2 *, Guan Liu2  \n1 Guangdong Institute of Smart Education, Jinan University, Guangzhou, China  \n2 School of Journalism and Communication, Jinan University, Guangzhou, China  \n*Corresponding author: [tfzhao@jnu.edu.cn](tfzhao@jnu.edu.cn)  \narXiv :2508 .03 174v4 [ cs .AI] 13 Jul 2026  \nAbstract—Collaborative partnerships play a crucial role in inquiry-oriented education. However, most learning partners are currently assigned through experience-driven heuristics or rulebased machine assistants, which often result in limited knowledge expansion and low adaptability. To address these challenges, this study introduces InqEduAgent, an LLM-empowered generative agent framework designed to simulate and select adaptive learning partners for inquiry-based learning. InqEduAgent integratesa Gaussian process–augmented matching mechanism to model the cognitive and evaluative characteristics of learners, allowing adaptive partner selection based on prior knowledge patterns. Comprehensive experiments demonstrate that InqEduAgent consistently achieves superior performance across diverse learning scenarios and large language model configurations. This study advances human–AI collaborative learning by enabling intelligent pairing between human- and AI-based learning partners, and contributes to adaptive user modeling and personalized recommendation within Web-based educational environments.  \nIndex Terms—AI agent, AI learning partner, personalized recommendation, adaptive learning systems.  \nI. INTRODUCTION  \nInquiry-oriented education has gained significant traction asan effective approach for fostering metacognitive skills, including critical thinking, self-regulated learning, questioning, and explanation [1], [2] Collaborative partnerships are a typical form of human–AI collaboration and play a crucial role in this paradigm.  \nExisting human-AI collaborations can be classified into three major categories. The first category includes upgraded versions of classic human–computer interaction systems, including personalized recommendation systems [3], AI-assisted home tutoring services [4], computer-supported cooperative work [5], and AI Assistance in Home Tutoring Services. These platforms are capable of generating personalized learning programs and plans, yet they regard machines as mere objects while overlooking the two-way interaction between learners and machines.  \nAI tutoring systems are the second category of research. Examples include medical surgical simulation technology instructors [6], programming tutoring systems [7], AI instructors for older adults [8], and AI instructors’ communication styles  \nThis work was supported in part by Major Program of the National Natural Science Foundation of China under Grant 2026ZD1500300, in part by National Natural Science Foundation of China under Grant 62206112, and in part by Key Laboratory of Smart Education of Guangdong Higher Education Institutes under Grant 2022LSYS003 .  \n[9] . These systems, seeing AI as a supertool, aim to enhance the teaching and learning experience in AI-enabled educational contexts. However, they rely heavily on predefined models, algorithms or the accuracy of the data used for training, which are hard to adapt to unforeseen learning situations and student needs that deviate from the norm.  \nHuman–AI co-learning patterns represent the third category and a future research direction. Studies in this direction focus on cooperative learning strategies, comparisons between AI and human teammates, and trustworthy human–AI partnerships [10]–[12] . These studies show that dynamic shifts between individual and collaborative learning can lead to a more comprehensive educational experience. This study falls into the third category of research. However, two key challenges remain in this area. Designing personalized AI co-learners that can enhance learners’ academic performance ","cbCaioR54Jw2DZED","https://ap.wps.com/l/cbCaioR54Jw2DZED","pdf",434414,3,1,7,"English","en",105,"# Introduction\n## Collaborative partnerships in inquiry-oriented education\n## Existing human–AI collaboration categories and limitations\n## Generative agents and LLMs in intelligent education","[{\"question\":\"What problem does InqEduAgent address in inquiry-oriented education?\",\"answer\":\"It targets limited adaptability and knowledge expansion caused by experience-based heuristics or rule-based learning assistants when assigning learning partners.\"},{\"question\":\"How does InqEduAgent select learning partners adaptively?\",\"answer\":\"It uses a Gaussian process–augmented matching mechanism to model learners’ cognitive and evaluative characteristics, then selects partners based on prior knowledge patterns.\"},{\"question\":\"What do experiments indicate about InqEduAgent’s effectiveness?\",\"answer\":\"Comprehensive experiments show superior performance across diverse learning scenarios and across different large language model configurations.\"}]",1784203518,18,{"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},"inqeduagent-adaptive-ai-learning-partners-with-gaussian-process-augmentation","",{"@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/inqeduagent-adaptive-ai-learning-partners-with-gaussian-process-augmentation/85438/",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",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does InqEduAgent address in inquiry-oriented education?","Question",{"text":75,"@type":76},"It targets limited adaptability and knowledge expansion caused by experience-based heuristics or rule-based learning assistants when assigning learning partners.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does InqEduAgent select learning partners adaptively?",{"text":80,"@type":76},"It uses a Gaussian process–augmented matching mechanism to model learners’ cognitive and evaluative characteristics, then selects partners based on prior knowledge patterns.",{"name":82,"@type":73,"acceptedAnswer":83},"What do experiments indicate about InqEduAgent’s effectiveness?",{"text":84,"@type":76},"Comprehensive experiments show superior performance across diverse learning scenarios and across different large language model configurations.","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},[93,97,101,105,110,115,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":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":22,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},"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":106,"slug":137},19,"General","general"]