ARPG+: Teaching Students to Ask Effective Questions for Educational LLM Use

ARPG+: Teaching Students to Ask Effective Questions for Educational LLM Use | 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 Research Article ARPG+: Teaching Students to Ask Effective Questions for Educational LLM Use Pei-Gen Ye, Kanghua Mo, Yucheng Long, Mengyun Liu, Haiwei Sang, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9084967/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 Despite widespread adoption of large language models (LLMs), most students cannot effectively prompt them. The core challenge is teaching students how to ask: transforming prompting from trial-and-error guessing into a systematic, transferable skill. Existing solutions, such as static templates, rule-based hints, and automated rewriting, either ignore individual learning needs or optimize outputs without building competence, leaving students dependent and unable to generalize. ARPG+ is a real-time coaching system grounded in cognitive load theory and zone of proximal development that senses when learners struggle, delivers calibrated just-in-time interventions, and fades support as skills develop. The system tracks learner capability with uncertainty quantification, estimates cognitive overload from behavioral signals, diagnoses prompt quality across six dimensions, and adapts scaffolding intensity through a dynamic schedule with periodic skill probes. A lightweight-deep dual architecture ensures fast responsiveness for routine interactions while reserving richer analysis for critical moments. Evaluation with simulated learners shows ARPG+ produces improvements: prompt quality increases 143% beyond unguided practice, learners achieve independence in 91% of final interactions versus 59% under fixed support, and the approach generalizes to other domains without retraining. Our work establishes that principled real-time coaching can improve prompt quality, accelerate learning, prevent cognitive overload, and foster durable autonomy. Large language models Real-Time Coaching Cognitive Load Theory Adaptive Scaffolding Human-AI Interaction Full Text Additional Declarations No competing interests reported. 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-9084967","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":622118361,"identity":"f21e853a-c210-49ef-8f1c-51858626a7b9","order_by":0,"name":"Pei-Gen Ye","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAxUlEQVRIiWNgGAWjYJACZiCWAzEOPCBFizFYSwIpWhIbQCyitBjcbr+6ubDtcPr8sMMPgbbYyek2ENJy50zZ7RlnDuduvJ1mANSSbGx2gJCWGzlpt3kqgFpmJ4C0HEjcRpwWg8PphrPTPxCrJf0YyJYEeekcIm2RvHOG7TbPmXTDDdI5BQcSDIjwC9/t9me3edus5eVnp2/+8KHCTo6gFoUbPAZAqpnBAKzSgIByEJCfwf4ASNUxyDcQoXoUjIJRMApGJgAAM/FN3Hr+zRwAAAAASUVORK5CYII=","orcid":"","institution":"Beijing Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Pei-Gen","middleName":"","lastName":"Ye","suffix":""},{"id":622118362,"identity":"2e222e4a-473e-4315-9d1d-cbe70cc57d07","order_by":1,"name":"Kanghua Mo","email":"","orcid":"","institution":"Beijing Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Kanghua","middleName":"","lastName":"Mo","suffix":""},{"id":622118363,"identity":"c5b1cb95-a210-4a24-93c9-f57b2ff6edf9","order_by":2,"name":"Yucheng Long","email":"","orcid":"","institution":"Beijing Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Yucheng","middleName":"","lastName":"Long","suffix":""},{"id":622118364,"identity":"94d51a8f-4cec-46ce-91b9-b413e3f6612a","order_by":3,"name":"Mengyun Liu","email":"","orcid":"","institution":"Hong Kong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Mengyun","middleName":"","lastName":"Liu","suffix":""},{"id":622118365,"identity":"cca66bad-15ec-41fd-9124-cab18d26a03c","order_by":4,"name":"Haiwei Sang","email":"","orcid":"","institution":"Guizhou Education University","correspondingAuthor":false,"prefix":"","firstName":"Haiwei","middleName":"","lastName":"Sang","suffix":""},{"id":622118366,"identity":"7cb32339-94e4-4aa7-984f-f012471ec644","order_by":5,"name":"Jun Zheng","email":"","orcid":"","institution":"Beijing Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Jun","middleName":"","lastName":"Zheng","suffix":""}],"badges":[],"createdAt":"2026-03-10 14:08:36","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9084967/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9084967/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107480945,"identity":"eaefc073-116a-4fad-a16f-417cd79f9754","added_by":"auto","created_at":"2026-04-22 02:14:39","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3655261,"visible":true,"origin":"","legend":"","description":"","filename":"InternationalJournalofEducationalTechnologyinHigherEducationAnonymous.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9084967/v1_covered_362f3a12-33f7-4fbd-b2c4-ea3fbab0d760.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"ARPG+: Teaching Students to Ask Effective Questions for Educational LLM Use","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"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, Real-Time Coaching, Cognitive Load Theory, Adaptive Scaffolding, Human-AI Interaction","lastPublishedDoi":"10.21203/rs.3.rs-9084967/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9084967/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Despite widespread adoption of large language models (LLMs), most students cannot effectively prompt them. The core challenge is teaching students how to ask: transforming prompting from trial-and-error guessing into a systematic, transferable skill. Existing solutions, such as static templates, rule-based hints, and automated rewriting, either ignore individual learning needs or optimize outputs without building competence, leaving students dependent and unable to generalize. ARPG+ is a real-time coaching system grounded in cognitive load theory and zone of proximal development that senses when learners struggle, delivers calibrated just-in-time interventions, and fades support as skills develop. The system tracks learner capability with uncertainty quantification, estimates cognitive overload from behavioral signals, diagnoses prompt quality across six dimensions, and adapts scaffolding intensity through a dynamic schedule with periodic skill probes. A lightweight-deep dual architecture ensures fast responsiveness for routine interactions while reserving richer analysis for critical moments. Evaluation with simulated learners shows ARPG+ produces improvements: prompt quality increases 143% beyond unguided practice, learners achieve independence in 91% of final interactions versus 59% under fixed support, and the approach generalizes to other domains without retraining. Our work establishes that principled real-time coaching can improve prompt quality, accelerate learning, prevent cognitive overload, and foster durable autonomy.","manuscriptTitle":"ARPG+: Teaching Students to Ask Effective Questions for Educational LLM Use","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-15 22:40:24","doi":"10.21203/rs.3.rs-9084967/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":"390d47b3-5ec4-4b23-acbd-998acd189747","owner":[],"postedDate":"April 15th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-12T10:16:04+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-18T09:08:17+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-15 22:40:24","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9084967","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9084967","identity":"rs-9084967","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}