Large Language Models in Student Simulation: A Survey

Large Language Models in Student Simulation: A Survey | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Systematic Review Large Language Models in Student Simulation: A Survey Xinxian Tian, Guanzhong Pan, Haibo Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8148343/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Large language models (LLMs) are transforming educational research. Within its many usage, LLM-based simulations emerge as a powerful paradigm for modeling student cognition, behavior, and learning variability. In this survey, we systematically review recent advances in LLM-driven student simulation, examining how researchers adapt, fine-tune, or prompt models to emulate varying levels of student proficiency and engagement. In addition, we categorize existing studies based on their simulation objectives, model adaptation strategies, and validation methodologies. Our survey offers a technological overview to help educators and researchers understand the potential of LLMs to advance educational research and practice. Artificial Intelligence and Machine Learning Large Language Models (LLMs) Student Simulation Educational Data Mining Synthetic Learners Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8148343","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Systematic Review","associatedPublications":[],"authors":[{"id":547113009,"identity":"e4445e63-d9f5-427a-b73b-750e672c1427","order_by":0,"name":"Xinxian Tian","email":"","orcid":"","institution":"The University of Edinburgh","correspondingAuthor":false,"prefix":"","firstName":"Xinxian","middleName":"","lastName":"Tian","suffix":""},{"id":547113010,"identity":"2286cb50-d9e7-4938-a605-a3d5534db4ff","order_by":1,"name":"Guanzhong Pan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5UlEQVRIiWNgGAWjYHACNhAhB8QGCDEevDqYwVqMSdeS2EC0Fv7Z54895t1zJ71/dvO2Dx/bGOR1ZyQwPnjbhluLxLlkdmOeZ89yZ9w5VjxzZhuD4bYbCcyGc/FoYTjDzCbNc+BwbsONHGNm3m0MCWY3EtikefFokYdqSZcHafkL0cL+G58WA6iWBAOQFkaoLcz4tBieYTaTnHPgmeHGG2nFjL3/JAy3nXnYLDnnHG4tcmcYn0m8OXBHXu5G8maGH2ds5M2OJx/88KYMj/ch4ACMIQHEjA0E1SNrGQWjYBSMglGACQBL+FCU5qxJxgAAAABJRU5ErkJggg==","orcid":"","institution":"Carnegie Mellon University","correspondingAuthor":true,"prefix":"","firstName":"Guanzhong","middleName":"","lastName":"Pan","suffix":""},{"id":547113011,"identity":"3ac33a3f-1781-4a15-98ca-00f9d2ea8d1d","order_by":2,"name":"Haibo Wang","email":"","orcid":"","institution":"Carnegie Mellon University","correspondingAuthor":false,"prefix":"","firstName":"Haibo","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2025-11-18 18:30:17","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8148343/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8148343/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96363823,"identity":"c436705a-c9ed-4b88-9800-8ea1cbaa393b","added_by":"auto","created_at":"2025-11-20 10:08:06","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":540567,"visible":true,"origin":"","legend":"","description":"","filename":"LLMinStudentSimulation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8148343/v1_covered_fafc7257-285c-4d06-aee4-16cd412f077e.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eLarge Language Models in Student Simulation: A Survey\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Carnegie Mellon University","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Large Language Models (LLMs), Student Simulation, Educational Data Mining, Synthetic Learners","lastPublishedDoi":"10.21203/rs.3.rs-8148343/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8148343/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eLarge language models (LLMs) are transforming educational research. Within its many usage, LLM-based simulations emerge as a powerful paradigm for modeling student cognition, behavior, and learning variability. In this survey, we systematically review recent advances in LLM-driven student simulation, examining how researchers adapt, fine-tune, or prompt models to emulate varying levels of student proficiency and engagement. In addition, we categorize existing studies based on their simulation objectives, model adaptation strategies, and validation methodologies. Our survey offers a technological overview to help educators and researchers understand the potential of LLMs to advance educational research and practice.\u003c/p\u003e","manuscriptTitle":"Large Language Models in Student Simulation: A Survey","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-19 08:50:50","doi":"10.21203/rs.3.rs-8148343/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"f39cd44a-cc52-4915-9688-2c7a2c198241","owner":[],"postedDate":"November 19th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":58207498,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-11-19T08:50:50+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-19 08:50:50","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8148343","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8148343","identity":"rs-8148343","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}