ARPG+: a simulation-based study of real-time coaching for educational LLM prompting.
Saved in:
| Title: | ARPG+: a simulation-based study of real-time coaching for educational LLM prompting. |
|---|---|
| Authors: | Ye, Pei-Gen1 (AUTHOR) ypgmhxy@gmail.com, Mo, Kanghua1 (AUTHOR) mokanghua@gmail.com, Long, Yucheng1 (AUTHOR) yuchenglong@e.gzhu.edu.cn, Liu, Mengyun2 (AUTHOR) lmy4pub@gmail.com, Sang, Haiwei3 (AUTHOR) haiweisang@gznc.edu.cn, Zheng, Jun1 (AUTHOR) zhengjun@bit.edu.cn |
| Source: | International Journal of Educational Technology in Higher Education. 6/17/2026, Vol. 23 Issue 1, p1-33. 33p. |
| Subject Terms: | *Cognitive load, *Learner autonomy, *Educational technology, *Instructional systems, *Tutors & tutoring, Prompt engineering, Simulation methods & models, Language models |
| 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. All reported evaluations are conducted on LLM-based simulated learners; the present work does not yet constitute empirical validation with real students, and classroom validation in authentic educational settings is identified as a necessary subsequent step. [ABSTRACT FROM AUTHOR] |
| Copyright of International Journal of Educational Technology in Higher Education is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Education Research Complete |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: ehh DbLabel: Education Research Complete An: 194611883 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: ARPG+: a simulation-based study of real-time coaching for educational LLM prompting. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Ye%2C+Pei-Gen%22">Ye, Pei-Gen</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> ypgmhxy@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Mo%2C+Kanghua%22">Mo, Kanghua</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> mokanghua@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Long%2C+Yucheng%22">Long, Yucheng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> yuchenglong@e.gzhu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Liu%2C+Mengyun%22">Liu, Mengyun</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> lmy4pub@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Sang%2C+Haiwei%22">Sang, Haiwei</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> haiweisang@gznc.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Zheng%2C+Jun%22">Zheng, Jun</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> zhengjun@bit.edu.cn</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Educational+Technology+in+Higher+Education%22">International Journal of Educational Technology in Higher Education</searchLink>. 6/17/2026, Vol. 23 Issue 1, p1-33. 33p. – Name: Subject Label: Subject Terms Group: Su Data: *<searchLink fieldCode="DE" term="%22Cognitive+load%22">Cognitive load</searchLink><br />*<searchLink fieldCode="DE" term="%22Learner+autonomy%22">Learner autonomy</searchLink><br />*<searchLink fieldCode="DE" term="%22Educational+technology%22">Educational technology</searchLink><br />*<searchLink fieldCode="DE" term="%22Instructional+systems%22">Instructional systems</searchLink><br />*<searchLink fieldCode="DE" term="%22Tutors+%26+tutoring%22">Tutors & tutoring</searchLink><br /><searchLink fieldCode="DE" term="%22Prompt+engineering%22">Prompt engineering</searchLink><br /><searchLink fieldCode="DE" term="%22Simulation+methods+%26+models%22">Simulation methods & models</searchLink><br /><searchLink fieldCode="DE" term="%22Language+models%22">Language models</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: 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. All reported evaluations are conducted on LLM-based simulated learners; the present work does not yet constitute empirical validation with real students, and classroom validation in authentic educational settings is identified as a necessary subsequent step. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of International Journal of Educational Technology in Higher Education is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=ehh&AN=194611883 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1186/s41239-026-00606-9 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 33 StartPage: 1 Subjects: – SubjectFull: Cognitive load Type: general – SubjectFull: Learner autonomy Type: general – SubjectFull: Educational technology Type: general – SubjectFull: Instructional systems Type: general – SubjectFull: Tutors & tutoring Type: general – SubjectFull: Prompt engineering Type: general – SubjectFull: Simulation methods & models Type: general – SubjectFull: Language models Type: general Titles: – TitleFull: ARPG+: a simulation-based study of real-time coaching for educational LLM prompting. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Ye, Pei-Gen – PersonEntity: Name: NameFull: Mo, Kanghua – PersonEntity: Name: NameFull: Long, Yucheng – PersonEntity: Name: NameFull: Liu, Mengyun – PersonEntity: Name: NameFull: Sang, Haiwei – PersonEntity: Name: NameFull: Zheng, Jun IsPartOfRelationships: – BibEntity: Dates: – D: 17 M: 06 Text: 6/17/2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 23659440 Numbering: – Type: volume Value: 23 – Type: issue Value: 1 Titles: – TitleFull: International Journal of Educational Technology in Higher Education Type: main |
| ResultId | 1 |
