[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118190-en":3,"doc-seo-118190-105":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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},118190,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Survey of Computerized Adaptive Testing - A Machine Learning Perspective","Computerized Adaptive Testing (CAT) delivers efficient, personalized proficiency assessment by selecting questions dynamically according to each examinee’s responses. Compared with non-adaptive testing, CAT can reduce the number of items while improving estimation accuracy, enabling broader adoption across education, healthcare, sports, and AI evaluation. As test settings grow in scale and complexity, machine learning increasingly complements traditional psychometrics. This survey focuses on CAT through a machine learning lens, covering measurement models, question selection, question-bank construction, and test control, and analyzing methods, strengths, limitations, and open challenges to support robust, fair, and effective CAT systems.","arXiv :2404 .00712v4 [ cs .LG] 15 Mar 2026  \nSurvey of Computerized Adaptive Testing: A Machine Learning Perspective  \nYan Zhuang, Qi Liu, Member, IEEE, Haoyang Bi, Zhenya Huang, Member, IEEE, Weizhe Huang, Jiatong Li, Junhao Yu, Zirui Liu, Zirui Hu, Yuting Hong, Zachary A. Pardos, Haiping Ma, Mengxiao Zhu, Member, IEEE, Shijin Wang, Enhong Chen, Fellow, IEEE  \nAbstract—Computerized Adaptive Testing (CAT) offers an efficient and personalized method for assessing examinee proficiency by dynamically adjusting test questions based on individual performance. Compared to traditional, non-personalized testing methods, CAT requires fewer questions and provides more accurate assessments. As a result, CAT has been widely adopted across various fields, including education, healthcare, sports, sociology, and the evaluation of AI models. While traditional methods rely on psychometrics and statistics, the increasing complexity of large-scale testing has spurred the integration of machine learning techniques. This paper aims to provide a machine learning-focused survey on CAT, presenting a fresh perspective on this adaptive testing paradigm. We delve into measurement models, question selection algorithm, bank construction, and test control within CAT, exploring how machine learning can optimize these components. Through an analysis of current methods, strengths, limitations, and challenges, we strive to develop robust, fair, and efficient CAT systems. By bridging psychometric-driven CAT research with machine learning, this survey advocates for a more inclusive and interdisciplinary approach to the future of adaptive testing.  \nIndex Terms—Adaptive testing, machine learning, proficiency assessment, AI evaluation, deep learning.  \n~~ ~~ ✦ ~~ ~~  \n1 INTRODUCTION  \nTHE assessment of intelligent agents, whether human or  \nAI systems, is essential for ensuring that individuals are well-prepared to meet the demands of their respective roles [1], [2] . For humans, assessment results can determine eligibility for opportunities such as admissions or employment. For AI models, these results can indicate whether a system is suitable for deployment and capable of making real-world decisions. Traditionally, assessments have often used a onesize-fits-all approach, where all examinees answer the same set of questions, and a final score is calculated. Examples include traditional paper-and-pencil tests for humans and various gold-standard benchmarks for AI models.  \nHowever, as the testing scale increases and the complexity and diversity of agents grow, traditional assessment methods face challenges in efficiency and reliability. Computerized Adaptive Testing (CAT), originating from psychometrics, offers a personalized testing paradigm by identifying and presenting the most informative and valuable questions to each examinee [3], [4] . This method has been widely adopted in high-stakes testing scenarios for humans, such as the SAT, GRE, and GMAT [5], [6] . Recently, CAT has also been increasingly used to assess AI’s capabilities, such as textual entailment recognition, chatbots, machine translation, and general-purpose AI systems [7], [8], [9], [10] . CAT approach  has been proved to require fewer questions  \n• Yan Zhuang, Qi Liu, Haoyang Bi, Zhenya Huang, Weizhe Huang, Jiatong Li, Junhao Yu, Zirui Liu, Zirui Hu, Yuting Hong, Mengxiao Zhu, and Enhong Chen are with State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, China. Yan Zhuang is also with Nanjing University of Aeronautics and Astronautics, China. Zachary A. Pardos is with University of California, Berkeley, USA. Haiping Ma is with Anhui University, China. Shijin Wang is with iFLYTEK Co., Ltd, China.  \nCorresponding E-mail: [qiliuql@ustc.edu.cn](qiliuql@ustc.edu.cn)  \nto achieve the same level of assessment accuracy for both humans and AI systems [11], [12] . Essentially, CAT aims to address a critical question about accuracy and efficiency: How to accurately","cbCairo0ZjCp4uhY","https://ap.wps.com/l/cbCairo0ZjCp4uhY","pdf",4868688,1,24,"English","en",105,"# Introduction\n# Computerized Adaptive Testing (CAT) Workflow\n## Measurement model\n## Question selection algorithm\n## Question bank construction and test control","[{\"question\":\"What problem does Computerized Adaptive Testing (CAT) aim to solve?\",\"answer\":\"CAT targets accurate and efficient estimation of an examinee’s true proficiency while minimizing the number of questions shown.\"},{\"question\":\"How does CAT decide which question to present next?\",\"answer\":\"CAT uses a measurement model to estimate current proficiency from prior responses, then a selection algorithm chooses the next item from a question bank using criteria such as informativeness and difficulty matching.\"},{\"question\":\"Which components control fairness and robustness in CAT?\",\"answer\":\"Test control manages factors including exposure balance, fairness, and robustness during the adaptive testing process.\"}]","Survey of Computerized Adaptive Testing - A Machine Learning Perspective | PDF",1785682097,60,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"survey-of-computerized-adaptive-testing-a-machine-learning-perspective","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"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":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/survey-of-computerized-adaptive-testing-a-machine-learning-perspective/118190/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does Computerized Adaptive Testing (CAT) aim to solve?","Question",{"text":75,"@type":76},"CAT targets accurate and efficient estimation of an examinee’s true proficiency while minimizing the number of questions shown.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does CAT decide which question to present next?",{"text":80,"@type":76},"CAT uses a measurement model to estimate current proficiency from prior responses, then a selection algorithm chooses the next item from a question bank using criteria such as informativeness and difficulty matching.",{"name":82,"@type":73,"acceptedAnswer":83},"Which components control fairness and robustness in CAT?",{"text":84,"@type":76},"Test control manages factors including exposure balance, fairness, and robustness during the adaptive testing process.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,134],{"id":20,"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":53,"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":29,"slug":108},5,"Comic","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":106,"slug":137},19,"General","general"]