View in EDS

Boosting Student Engagement in STEM: Integrating Large Language Model-Based Virtual Agents into Alternate Reality Games

Saved in:
Bibliographic Details
Title: Boosting Student Engagement in STEM: Integrating Large Language Model-Based Virtual Agents into Alternate Reality Games
Language: English
Authors: Minkai Wang (ORCID 0009-0003-9591-1076), Jingdong Zhu (ORCID 0009-0000-6188-0089), Gwo-Jen Hwang (ORCID 0000-0001-5155-276X), Shao-Chen Chang (ORCID 0000-0001-9446-1921), Qi-Fan Yang (ORCID 0000-0003-1791-985X), Di Zhang (ORCID 0000-0002-9010-0907)
Source: Journal of Computer Assisted Learning. 2025 41(6).
Availability: Wiley. Available from: John Wiley & Sons, Inc. 111 River Street, Hoboken, NJ 07030. Tel: 800-835-6770; e-mail: cs-journals@wiley.com; Web site: https://www.wiley.com/en-us
Peer Reviewed: Y
Page Count: 19
Publication Date: 2025
Document Type: Journal Articles
Reports - Research
Descriptors: Learner Engagement, STEM Education, Natural Language Processing, Artificial Intelligence, Technology Uses in Education, Educational Technology, Computer Simulation, Computer Games, Educational Games, Game Based Learning, Problem Solving, Academic Achievement, Metacognition, Predictor Variables
DOI: 10.1111/jcal.70139
ISSN: 0266-4909
1365-2729
Abstract: Background: STEM education aims to develop innovation and problem-solving skills through interdisciplinary learning, yet struggles to foster student engagement and interdisciplinary thinking. Whilst alternate reality games (ARGs) can boost motivation via game-based problem-solving, integrating large language models (LLMs) remains underexplored. LLM-based virtual agents offer new opportunities for adaptive support. Objectives: This study aimed to investigate the effectiveness of an LLM-assisted ARG system (LLM-ARG) in enhancing academic performance, metacognitive awareness, and engagement. Methods: A quasi-experimental study compared LLM-ARG with conventional ARG methods amongst primary school students. The experimental group used LLM-ARG with personalised virtual agent support, whilst the control group employed a conventional ARG with a traditional, rule-based virtual agent that offered only pre-scripted feedback. Data were collected through pre- and post-tests, metacognitive awareness questionnaires, and interaction logs. ANCOVA and correlation analyses were conducted. Results and Conclusions: LLM-ARG significantly improved learning achievements and metacognitive awareness compared to conventional ARG. High-frequency interactions promoted exploration but did not consistently enhance problem-solving, whilst low-frequency interactions led to higher success via goal-directed strategies. Metacognitive competence emerged as a key predictor of academic performance, highlighting the need to balance exploration with efficiency. This study demonstrates how LLM-driven scaffolding supports diverse learning strategies and promotes adaptive learning in STEM education.
Abstractor: As Provided
Entry Date: 2025
Accession Number: EJ1489797
Database: ERIC
FullText Text:
  Availability: 0
Header DbId: eric
DbLabel: ERIC
An: EJ1489797
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Boosting Student Engagement in STEM: Integrating Large Language Model-Based Virtual Agents into Alternate Reality Games
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Minkai+Wang%22">Minkai Wang</searchLink> (ORCID <externalLink term="https://orcid.org/0009-0003-9591-1076">0009-0003-9591-1076</externalLink>)<br /><searchLink fieldCode="AR" term="%22Jingdong+Zhu%22">Jingdong Zhu</searchLink> (ORCID <externalLink term="https://orcid.org/0009-0000-6188-0089">0009-0000-6188-0089</externalLink>)<br /><searchLink fieldCode="AR" term="%22Gwo-Jen+Hwang%22">Gwo-Jen Hwang</searchLink> (ORCID <externalLink term="https://orcid.org/0000-0001-5155-276X">0000-0001-5155-276X</externalLink>)<br /><searchLink fieldCode="AR" term="%22Shao-Chen+Chang%22">Shao-Chen Chang</searchLink> (ORCID <externalLink term="https://orcid.org/0000-0001-9446-1921">0000-0001-9446-1921</externalLink>)<br /><searchLink fieldCode="AR" term="%22Qi-Fan+Yang%22">Qi-Fan Yang</searchLink> (ORCID <externalLink term="https://orcid.org/0000-0003-1791-985X">0000-0003-1791-985X</externalLink>)<br /><searchLink fieldCode="AR" term="%22Di+Zhang%22">Di Zhang</searchLink> (ORCID <externalLink term="https://orcid.org/0000-0002-9010-0907">0000-0002-9010-0907</externalLink>)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="SO" term="%22Journal+of+Computer+Assisted+Learning%22"><i>Journal of Computer Assisted Learning</i></searchLink>. 2025 41(6).
– Name: Avail
  Label: Availability
  Group: Avail
  Data: Wiley. Available from: John Wiley & Sons, Inc. 111 River Street, Hoboken, NJ 07030. Tel: 800-835-6770; e-mail: cs-journals@wiley.com; Web site: https://www.wiley.com/en-us
– Name: PeerReviewed
  Label: Peer Reviewed
  Group: SrcInfo
  Data: Y
– Name: Pages
  Label: Page Count
  Group: Src
  Data: 19
– Name: DatePubCY
  Label: Publication Date
  Group: Date
  Data: 2025
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Journal Articles<br />Reports - Research
– Name: Subject
  Label: Descriptors
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Learner+Engagement%22">Learner Engagement</searchLink><br /><searchLink fieldCode="DE" term="%22STEM+Education%22">STEM Education</searchLink><br /><searchLink fieldCode="DE" term="%22Natural+Language+Processing%22">Natural Language Processing</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+Intelligence%22">Artificial Intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Technology+Uses+in+Education%22">Technology Uses in Education</searchLink><br /><searchLink fieldCode="DE" term="%22Educational+Technology%22">Educational Technology</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Simulation%22">Computer Simulation</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Games%22">Computer Games</searchLink><br /><searchLink fieldCode="DE" term="%22Educational+Games%22">Educational Games</searchLink><br /><searchLink fieldCode="DE" term="%22Game+Based+Learning%22">Game Based Learning</searchLink><br /><searchLink fieldCode="DE" term="%22Problem+Solving%22">Problem Solving</searchLink><br /><searchLink fieldCode="DE" term="%22Academic+Achievement%22">Academic Achievement</searchLink><br /><searchLink fieldCode="DE" term="%22Metacognition%22">Metacognition</searchLink><br /><searchLink fieldCode="DE" term="%22Predictor+Variables%22">Predictor Variables</searchLink>
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1111/jcal.70139
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 0266-4909<br />1365-2729
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Background: STEM education aims to develop innovation and problem-solving skills through interdisciplinary learning, yet struggles to foster student engagement and interdisciplinary thinking. Whilst alternate reality games (ARGs) can boost motivation via game-based problem-solving, integrating large language models (LLMs) remains underexplored. LLM-based virtual agents offer new opportunities for adaptive support. Objectives: This study aimed to investigate the effectiveness of an LLM-assisted ARG system (LLM-ARG) in enhancing academic performance, metacognitive awareness, and engagement. Methods: A quasi-experimental study compared LLM-ARG with conventional ARG methods amongst primary school students. The experimental group used LLM-ARG with personalised virtual agent support, whilst the control group employed a conventional ARG with a traditional, rule-based virtual agent that offered only pre-scripted feedback. Data were collected through pre- and post-tests, metacognitive awareness questionnaires, and interaction logs. ANCOVA and correlation analyses were conducted. Results and Conclusions: LLM-ARG significantly improved learning achievements and metacognitive awareness compared to conventional ARG. High-frequency interactions promoted exploration but did not consistently enhance problem-solving, whilst low-frequency interactions led to higher success via goal-directed strategies. Metacognitive competence emerged as a key predictor of academic performance, highlighting the need to balance exploration with efficiency. This study demonstrates how LLM-driven scaffolding supports diverse learning strategies and promotes adaptive learning in STEM education.
– Name: AbstractInfo
  Label: Abstractor
  Group: Ab
  Data: As Provided
– Name: DateEntry
  Label: Entry Date
  Group: Date
  Data: 2025
– Name: AN
  Label: Accession Number
  Group: ID
  Data: EJ1489797
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=eric&AN=EJ1489797
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1111/jcal.70139
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 19
    Subjects:
      – SubjectFull: Learner Engagement
        Type: general
      – SubjectFull: STEM Education
        Type: general
      – SubjectFull: Natural Language Processing
        Type: general
      – SubjectFull: Artificial Intelligence
        Type: general
      – SubjectFull: Technology Uses in Education
        Type: general
      – SubjectFull: Educational Technology
        Type: general
      – SubjectFull: Computer Simulation
        Type: general
      – SubjectFull: Computer Games
        Type: general
      – SubjectFull: Educational Games
        Type: general
      – SubjectFull: Game Based Learning
        Type: general
      – SubjectFull: Problem Solving
        Type: general
      – SubjectFull: Academic Achievement
        Type: general
      – SubjectFull: Metacognition
        Type: general
      – SubjectFull: Predictor Variables
        Type: general
    Titles:
      – TitleFull: Boosting Student Engagement in STEM: Integrating Large Language Model-Based Virtual Agents into Alternate Reality Games
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Minkai Wang
      – PersonEntity:
          Name:
            NameFull: Jingdong Zhu
      – PersonEntity:
          Name:
            NameFull: Gwo-Jen Hwang
      – PersonEntity:
          Name:
            NameFull: Shao-Chen Chang
      – PersonEntity:
          Name:
            NameFull: Qi-Fan Yang
      – PersonEntity:
          Name:
            NameFull: Di Zhang
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 12
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 0266-4909
            – Type: issn-electronic
              Value: 1365-2729
          Numbering:
            – Type: volume
              Value: 41
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: Journal of Computer Assisted Learning
              Type: main
ResultId 1