pith. sign in

arxiv: 2605.21962 · v1 · pith:KPXHQC4Lnew · submitted 2026-05-21 · 💻 cs.AI · cs.CY· cs.HC· cs.MA

AI-Enabled Serious Games: Integrating Intelligence and Adaptivity in Training Systems

Priyamvada Tripathi , Bill Kapralos This is my paper

Pith reviewed 2026-05-22 06:44 UTC · model grok-4.3

classification 💻 cs.AI cs.CYcs.HCcs.MA
keywords serious gamesinstructional adaptationlearner modelingintelligent tutoring systemsreinforcement learninglarge language modelsdynamic difficulty adjustmentadaptivity
0
0 comments X

The pith

Artificial intelligence can enable serious games to adapt training scenarios and feedback in real time by modeling what a learner knows.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Serious games used for training in healthcare, defense, and education often remain limited by fixed scenarios and weak personalization. The paper reviews how recent AI methods such as large language models, reinforcement learning, and agent architectures can supply instructional intelligence and adaptivity to overcome those limits. It traces a historical line from early computer-assisted instruction through intelligent tutoring systems to current AI-enabled designs. The review also flags open questions around explainability, validation, and the still-scarce evidence that these adaptations produce lasting learning gains.

Core claim

This chapter examines how contemporary AI approaches may support real-time instructional adaptation in serious games. It distinguishes between instructional intelligence, defined as a system's capacity to infer learner knowledge and reason about pedagogically appropriate responses, and adaptivity, defined as the ability to modify instructional actions during interaction. A historical synthesis of adaptive learning systems is presented, tracing developments from early computer-assisted instruction through intelligent tutoring systems, dynamic difficulty adjustment, authoring platforms, learning analytics, and recent AI-enabled architectures. Building on this perspective, the chapter discusses

What carries the argument

Instructional intelligence and adaptivity, where the first infers learner knowledge and reasons about suitable responses while the second changes actions during play.

If this is right

  • Serious games can vary scenarios dynamically in response to detected learner states.
  • Contextual feedback and adaptive pacing become feasible during individual play sessions.
  • Learner-state modeling can support more precise personalization than earlier tutoring systems.
  • Agent-based architectures may combine intelligence and adaptivity into unified training loops.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Designers could automate large parts of scenario creation, lowering authoring effort for new training modules.
  • Questions of learner trust in AI decisions may require explicit transparency features before wide use in high-stakes domains.
  • Long-term outcome studies in specific fields such as medical procedure training would test whether short-term adaptation effects persist.

Load-bearing premise

That AI techniques such as large language models and reinforcement learning will deliver pedagogically effective real-time adaptations despite limited evidence on long-term learning results.

What would settle it

A multi-session controlled trial that measures skill retention and transfer in learners using an AI-adapted serious game versus a static version, with clear differences in outcome scores.

read the original abstract

Serious games are widely used for learning and training across domains such as healthcare, defense, and education. Persistent challenges remain, however, including static scenario design, authoring bottlenecks, limited learner modeling, and difficulty implementing meaningful real-time instructional adaptation. Recent advances in artificial intelligence (AI) introduce novel capabilities such as dynamic scenario variation, contextual feedback, adaptive pacing, and learner-state modeling that may help address some of these limitations. At the same time, integrating AI into serious games raises important questions related to validity, transparency, system control, and learner trust. This chapter examines how contemporary AI approaches may support real-time instructional adaptation in serious games. It distinguishes between instructional intelligence, defined as a system's capacity to infer learner knowledge and reason about pedagogically appropriate responses, and adaptivity, defined as the ability to modify instructional actions during interaction. A historical synthesis of adaptive learning systems is presented, tracing developments from early computer-assisted instruction through intelligent tutoring systems (ITS), dynamic difficulty adjustment (DDA), authoring platforms, learning analytics, and recent AI-enabled architectures. Building on this perspective, the chapter discusses how large language models (LLMs), reinforcement learning (RL), and agent-based architectures may contribute to more integrated forms of intelligence and adaptivity in serious games. It also highlights practical and research challenges associated with AI-enabled systems, including explainability, validation, computational cost, and the limited empirical evidence regarding long-term learning outcomes in AI-enabled serious games.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The manuscript is a perspective chapter offering a historical synthesis of adaptive learning systems in serious games, tracing developments from early computer-assisted instruction through intelligent tutoring systems, dynamic difficulty adjustment, authoring platforms, and learning analytics. It defines instructional intelligence as the capacity to infer learner knowledge and reason about pedagogically appropriate responses, and adaptivity as the ability to modify instructional actions in real time. Building on this, the chapter examines potential contributions from large language models, reinforcement learning, and agent architectures to address challenges like static scenarios and limited learner modeling, while noting open issues around validity, transparency, computational cost, and limited empirical evidence on long-term outcomes.

Significance. The manuscript provides a balanced, scoped overview that correctly uses tentative language and flags evidentiary gaps, making it a constructive contribution to the AI-for-education literature. The explicit distinction between intelligence and adaptivity, combined with the enumeration of practical challenges, supplies a useful framing for future work on AI-enabled training systems. No new empirical results or derivations are claimed, so the value lies in synthesis and problem identification rather than novel predictions.

major comments (1)
  1. Abstract and section on AI contributions: the statement that LLMs, RL, and agent architectures 'may help address some of these limitations' is appropriately hedged, yet the manuscript does not supply even one concrete mapping (e.g., how an RL policy would select between contextual feedback and adaptive pacing in a given game state). Because this mapping is central to the claim that contemporary AI can move beyond historical limitations, a brief illustrative scenario or reference to an existing prototype would strengthen the argument without altering its tentative tone.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive review, positive assessment of the manuscript as a balanced synthesis, and recommendation for minor revision. We address the single major comment below.

read point-by-point responses

  1. Referee: Abstract and section on AI contributions: the statement that LLMs, RL, and agent architectures 'may help address some of these limitations' is appropriately hedged, yet the manuscript does not supply even one concrete mapping (e.g., how an RL policy would select between contextual feedback and adaptive pacing in a given game state). Because this mapping is central to the claim that contemporary AI can move beyond historical limitations, a brief illustrative scenario or reference to an existing prototype would strengthen the argument without altering its tentative tone.

    Authors: We agree that a concrete mapping would help illustrate how contemporary AI techniques could extend beyond historical limitations in serious games. Although the chapter is a perspective synthesis rather than a technical implementation paper, we will add a brief hypothetical scenario to the section discussing AI contributions. This example will describe, for instance, an RL policy trained to select between delivering LLM-generated contextual feedback or adjusting pacing based on inferred learner state in a defense training simulation, framed tentatively to maintain the manuscript's overall tone and without claiming new empirical results. revision: yes

Circularity Check

0 steps flagged

No significant circularity in derivation chain

full rationale

The paper is a narrative review and perspective chapter that synthesizes historical developments in adaptive learning systems from early CAI through ITS, DDA, and learning analytics, then discusses potential contributions of LLMs, RL, and agent architectures to instructional intelligence and adaptivity in serious games. It presents no mathematical derivations, equations, fitted parameters, or predictive models. All claims are framed with tentative phrasing such as 'may help address' and explicitly flag limited empirical evidence on long-term outcomes, validity, and transparency, so the argument remains self-contained without reducing to self-citation chains, self-definitions, or renamed inputs.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

As a review chapter the paper introduces no new free parameters, axioms, or invented entities; it discusses established concepts from computer-assisted instruction, intelligent tutoring systems, and recent AI methods.

pith-pipeline@v0.9.0 · 5800 in / 1092 out tokens · 44179 ms · 2026-05-22T06:44:31.634697+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

103 extracted references · 103 canonical work pages · 2 internal anchors

  1. [1]

    Trust in AI: Progress, Challenges, and Future Directions

    S. Afroogh, A. Akbari, E. Malone, et al. “Trust in AI: Progress, Challenges, and Future Directions”. In:Humanities and Social Sciences Communications 11.1568 (2024).doi:10.1057/s41599-024-04044-8

    work page doi:10.1057/s41599-024-04044-8 2024

  2. [2]

    S. M. Alessi and S. R. Trollip.Computer-Based Instruction: Methods and Development. Prentice-Hall, 1985

    work page 1985

  3. [3]

    Instruction Based on Adaptive Learning Technologies

    V. Aleven et al. “Instruction Based on Adaptive Learning Technologies”. In: Handbook of Research on Learning and Instruction. Ed. by R. E. Mayer and P. Alexander. 2nd. New York: Routledge, 2017, pp. 522–560

    work page 2017

  4. [4]

    Cognitive Tutors: Lessons Learned

    J. R. Anderson et al. “Cognitive Tutors: Lessons Learned”. In:Journal of the Learning Sciences4.2 (1995), pp. 167–207.doi:10.1207/s15327809jls0402_ 2

    work page doi:10.1207/s15327809jls0402_ 1995

  5. [5]

    Anderson and David R

    Lorin W. Anderson and David R. Krathwohl.A Taxonomy for Learning, Teach- ing, and Assessing: A Revision of Bloom’s Taxonomy of Educational Objectives: Complete Edition. New York: Longman, 2001

    work page 2001

  6. [6]

    Anderson and Lauren A

    Lorin W. Anderson and Lauren A. Sosniak, eds.Bloom’s Taxonomy: A Forty- Year Retrospective. Ninety-Third Yearbook of the National Society for the Study 22 Priyamvada Tripathi and Bill Kapralos of Education, Part II. Chicago, IL: University of Chicago Press, 1994.isbn: 0-226-60164-1

    work page 1994

  7. [7]

    Challenge-Sensitive Action Selection: An Application to Game Balancing

    G. Andrade et al. “Challenge-Sensitive Action Selection: An Application to Game Balancing”. In:Proceedings of the IEEE/WIC/ACM International Con- ference on Intelligent Agent Technology. IEEE, 2005, pp. 194–200.doi:10. 1109/IAT.2005.52

    work page 2005

  8. [8]

    Educational Data Mining and Learning Analyt- ics

    R. S. Baker and P. S. Inventado. “Educational Data Mining and Learning Analyt- ics”. In:Learning Analytics: From Research to Practice. Ed. by J. A. Larusson and B. White. Springer, 2014, pp. 61–75.doi:10.1007/978-1-4614-3305- 7_4

    work page doi:10.1007/978-1-4614-3305- 2014

  9. [9]

    Enhancing Difficult Airway Management Training: The Role of Virtual Reality and Adaptive Learning

    E. Battegazzorre et al. “Enhancing Difficult Airway Management Training: The Role of Virtual Reality and Adaptive Learning”. In:Virtual Reality29.Article 22 (2025).doi:10.1007/s10055-025-01105-4

    work page doi:10.1007/s10055-025-01105-4 2025

  10. [10]

    Assessment in and of Serious Games: An Overview

    F. Bellotti et al. “Assessment in and of Serious Games: An Overview”. In: Advances in Human-Computer Interaction2013 (2013), Article 136864.doi: 10.1155/2013/136864

    work page doi:10.1155/2013/136864 2013

  11. [11]

    The Wide World of Computer-Based Education

    Donald Bitzer. “The Wide World of Computer-Based Education”. In: ed. by Morris Rubinoff and Marshall C. Yovits. Vol. 15. Advances in Computers. Elsevier, 1976, pp. 239–283.doi:https : / / doi . org / 10 . 1016 / S0065 - 2458(08)60523- 9.url:https://www.sciencedirect.com/science/ article/pii/S0065245808605239

    work page 1976

  12. [12]

    The AI Systems of Left 4 Dead

    Michael Booth. “The AI Systems of Left 4 Dead”. In:Proceedings of the 5th AAAI Conference on Artificial Intelligence and Interactive Digital Entertain- ment (AIIDE 2009). Stanford, CA, 2009

    work page 2009

  13. [13]

    J. D. Bransford, A. L. Brown, and R. R. Cocking.How People Learn: Brain, Mind, Experience, and School. National Academy Press, 1999

    work page 1999

  14. [14]

    Learning about Social Learning in MOOCs: From Sta- tistical Analysis to Generative Model

    C. G. Brinton et al. “Learning about Social Learning in MOOCs: From Sta- tistical Analysis to Generative Model”. In:IEEE Transactions on Learning Technologies7.4 (2014), pp. 346–359.doi:10.1109/TLT.2014.2337900

    work page doi:10.1109/tlt.2014.2337900 2014

  15. [15]

    Language Models Are Few-Shot Learners

    T. Brown et al. “Language Models Are Few-Shot Learners”. In:Advances in Neural Information Processing Systems. Vol. 33. 2020, pp. 1877–1901

    work page 2020

  16. [16]

    User Models for Adaptive Hypermedia and Adaptive Educational Systems

    P. Brusilovsky and E. Mill ´an. “User Models for Adaptive Hypermedia and Adaptive Educational Systems”. In:The Adaptive Web: Methods and Strategies of Web Personalization. Vol. 4321. Lecture Notes in Computer Science. Berlin Heidelberg New York: Springer-Verlag, 2007

    work page 2007

  17. [17]

    Adaptive Hypermedia

    Peter Brusilovsky. “Adaptive Hypermedia”. In:User Modeling and User- Adapted Interaction11 (2001).doi:10.1023/A:1011143116306

    work page doi:10.1023/a:1011143116306 2001

  18. [18]

    Work Models: Beyond Instructional Objectives

    C. V. Bunderson et al. “Work Models: Beyond Instructional Objectives”. In: Instructional Science10.3 (1981), pp. 205–215.doi:10.1007/BF00139798

    work page doi:10.1007/bf00139798 1981

  19. [19]

    Emotion Assessment from Physiological Signals for Adap- tation of Game Difficulty

    G. Chanel et al. “Emotion Assessment from Physiological Signals for Adap- tation of Game Difficulty”. In:IEEE Transactions on Systems, Man, and Cy- bernetics, Part A: Systems and Humans41.6 (2011), pp. 1052–1063.doi: 10.1109/TSMCA.2011.2116000

    work page doi:10.1109/tsmca.2011.2116000 2011

  20. [20]

    Flow in Games (and Everything Else)

    Jenova Chen. “Flow in Games (and Everything Else)”. In:Communications of the ACM50 (2007), pp. 31–34.doi:10.1145/1232743.1232769. AI-Enabled Serious Games: Integrating Intelligence and Adaptivity in Training Systems 23

    work page doi:10.1145/1232743.1232769 2007

  21. [21]

    Self-Explanations: How Students Study and Use Examples in Learning to Solve Problems

    Michelene Chi et al. “Self-Explanations: How Students Study and Use Examples in Learning to Solve Problems”. In:Cognitive Science13 (1989), pp. 145–182. doi:10.1016/0364-0213(89)90002-5

    work page doi:10.1016/0364-0213(89)90002-5 1989

  22. [22]

    Cognitive Apprenticeship: Teaching the Crafts of Reading, Writing, and Mathematics

    Allan Collins, John Brown, and Susan Newman. “Cognitive Apprenticeship: Teaching the Crafts of Reading, Writing, and Mathematics”. In: 2018.doi: 10.4324/9781315044408-14

    work page doi:10.4324/9781315044408-14 2018

  23. [23]

    Virtual Patients Using Large Language Models: Scalable, Contextualized Simulation of Clinician-Patient Dialogue With Feedback

    David A. Cook et al. “Virtual Patients Using Large Language Models: Scalable, Contextualized Simulation of Clinician-Patient Dialogue With Feedback”. In: Journal of Medical Internet Research27 (2025), e68486.doi:10.2196/68486

    work page doi:10.2196/68486 2025

  24. [24]

    and Anderson, John R

    A. T. Corbett and J. R. Anderson. “Knowledge Tracing: Modeling the Ac- quisition of Procedural Knowledge”. In:User Modeling and User-Adapted Interaction4.4 (1995), pp. 253–278.doi:10.1007/BF01099821

    work page doi:10.1007/bf01099821 1995

  25. [25]

    Mihaly Csikszentmihalyi.Flow: The Psychology of Optimal Experience. 1990

    work page 1990

  26. [26]

    Cuban.Oversold and Underused: Computers in the Classroom

    L. Cuban.Oversold and Underused: Computers in the Classroom. Cambridge, MA: Harvard University Press, 2001

    work page 2001

  27. [27]

    A Review of Recent Advances in Learner and Skill Modeling in Intelligent Learning Environments

    Michel Desmarais and Ryan Baker. “A Review of Recent Advances in Learner and Skill Modeling in Intelligent Learning Environments”. In:User Modeling and User-Adapted Interaction22 (2012), pp. 9–38.doi:10.1007/s11257- 011-9106-8

    work page doi:10.1007/s11257- 2012

  28. [28]

    Item Response Theory

    S. Embretson and X. Yang. “Item Response Theory”. In:Handbook of Comple- mentary Methods in Education Research. Ed. by J. L. Green, G. Camilli, and P. B. Elmore. Lawrence Erlbaum Associates Publishers, 2006, pp. 385–409

    work page 2006

  29. [29]

    Springer, 2013.doi:10.1007/978-3-642-35329-1

    Jean-Claude Falmagne et al.Knowledge Spaces: Applications in Education. Springer, 2013.doi:10.1007/978-3-642-35329-1

    work page doi:10.1007/978-3-642-35329-1 2013

  30. [31]

    Learning Analytics: Drivers, Developments and Chal- lenges

    Rebecca Ferguson. “Learning Analytics: Drivers, Developments and Chal- lenges”. In:International Journal of Technology Enhanced Learning4 (2012), pp. 304–317.doi:10.1504/IJ.2012.051816

    work page doi:10.1504/ij.2012.051816 2012

  31. [32]

    Examining AI Use in Educational Contexts: A Scoping Meta-Review and Bibliometric Analysis

    Y. Fu, Z. Weng, and J. Wang. “Examining AI Use in Educational Contexts: A Scoping Meta-Review and Bibliometric Analysis”. In:International Journal of Artificial Intelligence in Education35 (2025), pp. 1388–1444.doi:10.1007/ s40593-024-00442-w

    work page 2025

  32. [33]

    (Springer Berlin Heidelberg, 2009)

    Stefan G ¨obel et al. “StoryTec: A Digital Storytelling Platform for the Authoring and Experiencing of Interactive and Non-linear Stories”. In:Fraunhofer IGD. Vol. 5334. Nov. 2008.isbn: 978-3-540-89424-7.doi:10.1007/978-3-540- 89454-4_40

    work page doi:10.1007/978-3-540- 2008

  33. [34]

    Systematic Review of Serious Games for Medical Education and Surgical Skills Training

    Maurits Graafland, Jan Maarten Schraagen, and Marlies Schijven. “Systematic Review of Serious Games for Medical Education and Surgical Skills Training”. In:British Journal of Surgery99 (2012), pp. 1322–1330.doi:10.1002/bjs. 8819

    work page doi:10.1002/bjs 2012

  34. [35]

    AutoTutor: A Tutor with Dialogue in Natural Lan- guage

    Arthur Graesser et al. “AutoTutor: A Tutor with Dialogue in Natural Lan- guage”. In:Behavior Research Methods36 (2004), pp. 180–192.doi:10 . 3758/BF03195563. 24 Priyamvada Tripathi and Bill Kapralos

    work page 2004

  35. [36]

    Reconsidering Fidelity in Simulation-Based Train- ing

    Stanley J. Hamstra et al. “Reconsidering Fidelity in Simulation-Based Train- ing”. In:Academic Medicine89.3 (Mar. 2014), pp. 387–392.doi:10.1097/ ACM.0000000000000130

    work page 2014

  36. [37]

    The Power of Feedback

    John Hattie and Helen Timperley. “The Power of Feedback”. In:Review of Edu- cational Research77.1 (2007), pp. 81–112.doi:10.3102/003465430298487

    work page doi:10.3102/003465430298487 2007

  37. [38]

    2023.doi:10.58863/20.500.12424/4276068

    Wayne Holmes, Maya Bialik, and Charles Fadel.Artificial Intelligence in Edu- cation. 2023.doi:10.58863/20.500.12424/4276068

    work page doi:10.58863/20.500.12424/4276068 2023

  38. [39]

    Student Learning Benefits of a Mixed-Reality Teacher Awareness Tool in AI-Enhanced Class- rooms

    Kenneth Holstein, Bruce McLaren, and Vincent Aleven. “Student Learning Benefits of a Mixed-Reality Teacher Awareness Tool in AI-Enhanced Class- rooms”. In: 2018.doi:10.1007/978-3-319-93843-1_12

    work page doi:10.1007/978-3-319-93843-1_12 2018

  39. [40]

    AI for Dynamic Difficulty Adjustment in Games

    Robin Hunicke and Vernell Chapman. “AI for Dynamic Difficulty Adjustment in Games”. In:Challenges in Game Artificial Intelligence, AAAI Workshop. Vol. 2. 2004

    work page 2004

  40. [41]

    Immersive Virtual Learning Environments for Healthcare Edu- cation: State-of-Art and Open Problems

    Bill Kapralos. “Immersive Virtual Learning Environments for Healthcare Edu- cation: State-of-Art and Open Problems”. In:Cureus16.9 (2024), e68483.doi: 10.7759/cureus.68483

    work page doi:10.7759/cureus.68483 2024

  41. [42]

    Levels of Fidelity and Multimodal Interactions

    Bill Kapralos et al. “Levels of Fidelity and Multimodal Interactions”. In:Tech- niques to Improve the Effectiveness of Serious Games. Ed. by P. Wouters and H. van Oostendorp. Springer Advances in Game-based Learning. Section: 5. 2017, pp. 79–101

    work page 2017

  42. [43]

    Productive Failure

    Manu Kapur and Ido Roll. “Productive Failure”. In:International Handbook of the Learning Sciences. Ed. by Frank Fischer et al. 2nd ed. New York: Routledge, 2023, pp. 190–199.isbn: 978-1-941804-72-8

    work page 2023

  43. [44]

    ChatGPT for Good? On Opportunities and Chal- lenges of Large Language Models for Education

    Enkelejda Kasneci et al. “ChatGPT for Good? On Opportunities and Chal- lenges of Large Language Models for Education”. In:Learning and Individual Differences103 (2023), p. 102274.doi:10.1016/j.lindif.2023.102274

    work page doi:10.1016/j.lindif.2023.102274 2023

  44. [45]

    What is Adaptive Training?

    C. R. Kelley. “What is Adaptive Training?” In:Human Factors11.6 (1969), pp. 547–556

    work page 1969

  45. [46]

    Exploring the Assistance Dilemma in Experiments with Cognitive Tutors

    Kenneth R. Koedinger and Vincent Aleven. “Exploring the Assistance Dilemma in Experiments with Cognitive Tutors”. In:Educational Psychology Review19 (2007), pp. 239–264.doi:10.1007/s10648-007-9049-0

    work page doi:10.1007/s10648-007-9049-0 2007

  46. [47]

    Instructional Com- plexity and the Science to Constrain It

    Kenneth R. Koedinger, Julie L. Booth, and David Klahr. “Instructional Com- plexity and the Science to Constrain It”. In:Science342.6161 (2013), pp. 935– 937.doi:10.1126/science.1238056

    work page doi:10.1126/science.1238056 2013

  47. [48]

    SHERLOCK: A Coached Practice Environment for an Electronics Troubleshooting Job

    Alan Lesgold et al. “SHERLOCK: A Coached Practice Environment for an Electronics Troubleshooting Job”. In:Computer-Assisted Instruction and Intel- ligent Tutoring Systems: Shared Goals and Complementary Approaches. Ed. by Jill H. Larkin and Ruth W. Chabay. Lawrence Erlbaum Associates, 1992, pp. 201–238

    work page 1992

  48. [49]

    Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

    Patrick Lewis et al. “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks”. In: (2020).doi:10.48550/arXiv.2005.11401

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2005.11401 2020

  49. [50]

    Deep Reinforcement Learning for Adaptive Learning Sys- tems

    Xiao Li et al. “Deep Reinforcement Learning for Adaptive Learning Sys- tems”. In:Journal of Educational and Behavioral Statistics48 (Nov. 2022), p. 107699862211298.doi:10.3102/10769986221129847. AI-Enabled Serious Games: Integrating Intelligence and Adaptivity in Training Systems 25

    work page doi:10.3102/10769986221129847 2022

  50. [51]

    Adaptivity Challenges in Games and Sim- ulations: A Survey

    Ricardo Lopes and Rafael Bidarra. “Adaptivity Challenges in Games and Sim- ulations: A Survey”. In:IEEE Transactions on Computational Intelligence and AI in Games3 (2011), pp. 85–99.doi:10.1109/TCIAIG.2011.2152841

    work page doi:10.1109/tciaig.2011.2152841 2011

  51. [52]

    Rosemary Luckin and Wayne Holmes.Intelligence Unleashed: An Argument for AI in Education. Tech. rep. 2016

    work page 2016

  52. [53]

    Ando and L

    Richard E. Mayer. “Computer Games in Education”. In:Annual Review of Psy- chology70 (2019), pp. 531–549.doi:10.1146/annurev- psych- 010418- 102744

    work page doi:10.1146/annurev- 2019

  53. [54]

    The Effectiveness of Online and Blended Learning: A Meta-Analysis of the Empirical Literature

    Barbara Means et al. “The Effectiveness of Online and Blended Learning: A Meta-Analysis of the Empirical Literature”. In:Teachers College Record115 (2013).doi:10.1177/016146811311500307

    work page doi:10.1177/016146811311500307 2013

  54. [55]

    Engineering Adaptive Serious Games Using Machine Learning

    Michael Miljanovic and Jeremy Bradbury. “Engineering Adaptive Serious Games Using Machine Learning”. In: May 2023, pp. 117–134.isbn: 978- 3-031-33337-8.doi:10.1007/978-3-031-33338-5_6

    work page doi:10.1007/978-3-031-33338-5_6 2023

  55. [56]

    ASPIRE: An Authoring System and Deployment En- vironment for Constraint-Based Tutors

    Antonija Mitrovic et al. “ASPIRE: An Authoring System and Deployment En- vironment for Constraint-Based Tutors”. In:International Journal of Artificial Intelligence in Education19.2 (2009), pp. 173–202

    work page 2009

  56. [57]

    Eleni Mitsea, Athanasios Drigas, and Charalampos Skianis. “A System- atic Review of Serious Games in the Era of Artificial Intelligence, Immer- sive Technologies, the Metaverse, and Neurotechnologies: Transformation Through Meta-Skills Training”. In:Electronics14.4 (2025), p. 649.doi: 10 . 3390 / electronics14040649.url:https : / / doi . org / 10 . 3390 /...

    work page 2025

  57. [59]

    Curriculum Learning for Reinforcement Learning Do- mains: A Framework and Survey

    Sanmit Narvekar et al. “Curriculum Learning for Reinforcement Learning Do- mains: A Framework and Survey”. In: (2020).doi:10.48550/arXiv.2003. 04960

    work page doi:10.48550/arxiv.2003 2020

  58. [60]

    Generative Large Lan- guage Models for Dialog-Based Tutoring: An Early Consideration of Op- portunities and Concerns

    Benjamin Nye, Dillon Mee, and Mark G. Core. “Generative Large Lan- guage Models for Dialog-Based Tutoring: An Early Consideration of Op- portunities and Concerns”. In:LLM@AIED. 2023.url:https : / / api . semanticscholar.org/CorpusID:262068884

    work page 2023

  59. [61]

    Edito- rial: Adaptivity in Serious Games Through Cognition-Based Analytics

    Herre van Oostendorp, Sander Bakkes, and Michael Kickmeier-Rust. “Edito- rial: Adaptivity in Serious Games Through Cognition-Based Analytics”. In: Frontiers in Education7 (2022).doi:10.3389/feduc.2022.911074

    work page doi:10.3389/feduc.2022.911074 2022

  60. [62]

    OpenAI.GPT-4 Technical Report. Tech. rep. Publication Title: ArXiv Volume: abs/2303.08774. 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  61. [63]

    Using Learning Analytics to Scale the Provision of Per- sonalised Feedback

    Abelardo Pardo et al. “Using Learning Analytics to Scale the Provision of Per- sonalised Feedback”. In:British Journal of Educational Technology50 (2017). doi:10.1111/bjet.12592

    work page doi:10.1111/bjet.12592 2017

  62. [64]

    The Social and Technological Dimensions of Scaffolding and Related Theoretical Concepts for Learning, Education, and Human Activity

    Roy Pea. “The Social and Technological Dimensions of Scaffolding and Related Theoretical Concepts for Learning, Education, and Human Activity”. In:Jour- nal of the Learning Sciences13 (2004).doi:10.1207/s15327809jls1303_6

    work page doi:10.1207/s15327809jls1303_6 2004

  63. [65]

    Deep Knowledge Tracing

    Chris Piech et al. “Deep Knowledge Tracing”. In:Advances in Neural Informa- tion Processing Systems 28 (NeurIPS 2015). 2015. 26 Priyamvada Tripathi and Bill Kapralos

    work page 2015

  64. [66]

    Foundations of Game- Based Learning

    Jan L. Plass, Bruce D. Homer, and Charles K. Kinzer. “Foundations of Game- Based Learning”. In:Educational Psychologist50.4 (2015), pp. 258–283.doi: 10.1080/00461520.2015.1122533

    work page doi:10.1080/00461520.2015.1122533 2015

  65. [67]

    A Systematic Review of Immersive Virtual Reality Applications for Higher Education: Design Elements, Lessons Learned, and Research Agenda

    Jaziar Radianti et al. “A Systematic Review of Immersive Virtual Reality Applications for Higher Education: Design Elements, Lessons Learned, and Research Agenda”. In:Computers & Education147 (2020), p. 103778.doi: 10.1016/j.compedu.2019.103778

    work page doi:10.1016/j.compedu.2019.103778 2020

  66. [68]

    A History of Instructional Design and Technology: Part II: A History of Instructional Design

    Robert A. Reiser. “A History of Instructional Design and Technology: Part II: A History of Instructional Design”. In:Educational Technology Research and Development49.2 (2001), pp. 57–67.url:http://www.jstor.org/ stable/30220311

    work page arXiv 2001

  67. [69]

    Ute Ritterfeld, Michael Cody, and Peter Vorderer.Serious Games: Mechanisms and Effects. 1st. Routledge, 2009.doi:10.4324/9780203891650

    work page doi:10.4324/9780203891650 2009

  68. [70]

    Educational Data Mining: A Re- view of the State of the Art

    Crist ´obal Romero and Sebastian Ventura. “Educational Data Mining: A Re- view of the State of the Art”. In:IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews40 (2010), pp. 601–618.doi: 10.1109/TSMCC.2010.2053532

    work page doi:10.1109/tsmcc.2010.2053532 2010

  69. [71]

    Russell and Peter Norvig.Artificial Intelligence: A Modern Approach

    Stuart J. Russell and Peter Norvig.Artificial Intelligence: A Modern Approach. 4th. Pearson, 2020

    work page 2020

  70. [72]

    The Defining Characteristics of Intelligent Tutoring Systems Re- search: ITSs Care, Precisely

    John Self. “The Defining Characteristics of Intelligent Tutoring Systems Re- search: ITSs Care, Precisely”. In:International Journal of Artificial Intelligence in Education10 (1998), pp. 350–364

    work page 1998

  71. [73]

    A Trainable Spaced Repetition Model for Language Learning

    Burr Settles and Brendan Meeder. “A Trainable Spaced Repetition Model for Language Learning”. In: 2016, pp. 1848–1858.doi:10.18653/v1/P16-1174

    work page doi:10.18653/v1/p16-1174 2016

  72. [74]

    Student Engagement in High School Classrooms from the Perspective of Flow Theory

    David J. Shernoff et al. “Student Engagement in High School Classrooms from the Perspective of Flow Theory”. In:School Psychology Quarterly18.2 (2003), pp. 158–176.doi:10.1521/scpq.18.2.158.21860

    work page doi:10.1521/scpq.18.2.158.21860 2003

  73. [75]

    Adaptive Educational Systems

    Valerie Shute and Diego Zapata-Rivera. “Adaptive Educational Systems”. In: Adaptive Technologies for Training and Education. 2012, pp. 7–27.doi:10. 1017/CBO9781139049580.004

    work page 2012

  74. [76]

    Focus on Formative Feedback

    Valerie J. Shute. “Focus on Formative Feedback”. In:Review of Educational Research78.1 (2008), pp. 153–189.doi:10.3102/0034654307313795

    work page doi:10.3102/0034654307313795 2008

  75. [77]

    Penetrating the Fog: Analytics in Learning and Education

    George Siemens and Phil Long. “Penetrating the Fog: Analytics in Learning and Education”. In:EDUCAUSE Review5 (2011), pp. 30–32.doi:10.17471/ 2499-4324/195

    work page 2011

  76. [78]

    2017, Na ture, 550, 354, doi: 10.1038/nature24270 9

    David Silver, Julian Schrittwieser, Karen Simonyan, et al. “Mastering the Game of Go Without Human Knowledge”. In:Nature550 (2017), pp. 354–359.doi: 10.1038/nature24270

    work page doi:10.1038/nature24270 2017

  77. [79]

    The Long History of Gaming in Military Training

    Roger Smith. “The Long History of Gaming in Military Training”. In:Simula- tion & Gaming41 (2010), pp. 6–19.doi:10.1177/1046878109334330

    work page doi:10.1177/1046878109334330 2010

  78. [80]

    Robert Sottilare.Design Recommendations for Intelligent Tutoring Systems – Volume 1: Learner Modeling. 2013

    work page 2013

  79. [81]

    A History of Computer- Based Instruction and Its Effects on Developing Instructional Technologies

    ¨Omer Faruk S¨ozc¨ u, .Ismail .Ipek, and Emine Tas ¸kın. “A History of Computer- Based Instruction and Its Effects on Developing Instructional Technologies”. In:European Researcher59.9-2 (2013), pp. 2341–2343. AI-Enabled Serious Games: Integrating Intelligence and Adaptivity in Training Systems 27

    work page 2013

  80. [82]

    Sutton and Andrew G

    Richard S. Sutton and Andrew G. Barto.Reinforcement Learning: An Introduc- tion. 2nd. Cambridge: The MIT Press, 2018.url:http://incompleteideas. net/book/the-book-2nd.html

    work page 2018

Showing first 80 references.