Designing GenAI Tools for Personalized Learning Implementation: Theoretical Analysis and Prototype of a Multi-Agent System

Abstract

Educator preparation, personalized learning (PL) implementation, and applications of Generative AI converge as three interrelated systems that, when carefully designed, can help achieve the long-sought goal of providing inclusive education for all learners. However, realizing this potential comes with challenges resulting from theoretical complexities and technological constraints. This article provides a theoretical analysis of the complex interconnectedness among these systems guided by the Cultural-Historical Activity Theory (CHAT). Building on the analysis, we introduce CoPL, a multi-agent system consisting of multiple agents with distinct functions that facilitate the complex PL design and engage pre-service teachers (PSTs) in dynamic conversations while prompting them to reflect on the inclusivity of agent-generated instructional suggestions. We describe the affordances and limitations of the system as a professional learning tool for PSTs to develop competencies for designing inclusive PL to meet diverse learning needs of all learners. Finally, we discuss future research on refining CoPL and its practical applications.

Keywords

personalized learning multi-agent system educator preparation inclusion and equity Cultural-Historical Activity Theory

Get full access to this article

View all access options for this article.

References

Aceves

T. C.

Kennedy

M. J.

(2024, February). High-leverage practices for students with disabilities (2nd ed.). Council for Exceptional Children and CEEDAR Center.

Archer

A. L.

Hughes

C. A.

(2010). Explicit instruction: Effective and efficient teaching. Guilford Publications.

Artiles

A. J.

Trent

S. C.

Hoffman-Kipp

Lopez-Torres

(2000). How do preservice teachers learn about culture, learning, and difference? From individual acquisition to cultural-historical practices in teacher education. Remedial and Special Education, 21, 79–80. https://doi.org/10.1177/088840640202500103

Bal

Waitoller

F. R.

Mawene

Gorham

(2020). Culture, context, and disability: A systematic literature review of cultural-historical activity theory-based studies on the teaching and learning of students with disabilities. Review of Education, Pedagogy, and Cultural Studies, 43(4), 293–337. https://doi.org/10.1080/10714413.2020.1829312

Bender

E. M.

Gebru

McMillan-Major

Shmitchell

(2021). On the dangers of stochastic parrots: Can language models be too big? Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency (pp. 610–623). https://doi.org/10.1145/3442188.3445922

Bernacki

M. L.

Lobczowski

N. G.

Greene

M. J.

(2021). A systematic review of research on PL: Personalized by whom, to what, how, and for what purpose(s)? Educational Psychology Review, 33, 1675–1715. https://doi.org/10.1007/s10648-021-09615-8

Billingsley

Bettini

(2019). Special education teacher attrition and retention: A review of the literature. Review of Educational Research, 89(5), 697–744. https://doi.org/10.3102/0034654319862495

Brown

T. B.

Mann

Ryder

Subbiah

Kaplan

Dhariwal

. . .Amodei

(2020). Language models are few-shot learners. arXiv. https://doi.org/10.48550/arXiv.2005.14165

Clemmensen

Kaptelinin

Nardi

(2016). Making HCI theory work: An analysis of the use of activity theory in HCI research. Behaviour & Information Technology, 35(8), 608–627. https://doi.org/10.1080/0144929X.2016.1175507

10.

DeepSeek-AI. (2025). DeepSeek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning [Preprint]. https://doi.org/10.48550/arXiv.2501.12948

11.

Dockterman

(2018). Insights from 200+ years of personalized learning. npj Science of Learning, 3(1), 15. https://doi.org/10.1038/s41539-018-0033-x

12.

Durante

Huang

Wake

Gong

Park

J. S.

Sarkar

. . .Gao

(2024). Agent AI: Surveying the horizons of multimodal interaction. arXiv preprint arXiv:2401.03568. https://doi.org/10.48550/arXiv.2401.03568

13.

Engeström

(1987). Learning by expanding: An activity theoretical approach to developmental research. Orienta-Konsultit.

14.

Fan

Tang

Shen

Tan

Zhao

. . .Gašević

(2025). Beware of metacognitive laziness: Effects of generative artificial intelligence on learning motivation, processes, and performance. British Journal of Educational Technology, 56, 489–530. https://doi.org/10.1111/bjet.13544

15.

Gallegos

I. O.

Rossi

R. A.

Barrow

Tanjim

M. M.

Kim

Dernoncourt

Zhang

Ahmed

N. K.

(2024). Bias and fairness in large language models: A survey. Computational Linguistics, 1–83. https://doi.org/10.1162/coli_a_00524

16.

Gao

Xiong

Gao

Jia

Pan

. . .Wang

(2023). Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997.

17.

Guo

Chen

Wang

Chang

Pei

Chawla

N. V.

. . .Zhang

(2024). Large language model based multi-agents: A survey of progress and challenges. arXiv preprint arXiv:2402.01680.

18.

Hadwin

Järvelä

Miller

(2018). Self-regulation, co-regulation, and shared regulation in collaborative learning environments. In Schunk

D. H.

Greene

J. A.

(Eds.), Handbook of self-regulation of learning and performance (pp.83–106). Routledge/Taylor & Francis Group.

19.

Hill-Jackson

V. J.

Craig

(2024). “Where the Good Ideas Are”: 75 Years of the Journal of Teacher Education. Journal of Teacher Education, 75(2), 129–140. https://doi.org/10.1177/00224871241232033

20.

Huang

Zhong

Feng

Wang

. . .Liu

(2024). A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. ACM Transactions on Information Systems, 43, 1–55. https://doi.org/10.1145/3703155

21.

Imundo

M. N.

Watanabe

Potter

A. H.

Gong

Arner

McNamara

D. S.

(2024). Expert thinking with generative chatbots. Journal of Applied Research in Memory and Cognition, 13(4), 465–484. https://doi.org/10.1037/mac0000199

22.

Karanasios

Nardi

Spinuzzi

Malaurent

(2021). Moving forward with activity theory in a digital world. Mind, Culture, and Activity, 28(3), 234–253. https://doi.org/10.1080/10749039.2021.1914662

23.

Lewis

Perez

Piktus

Petroni

Karpukhin

Goyal

. . .Kiela

(2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459–9474. https://dl.acm.org/doi/abs/10.5555/3495724.3496517

24.

Xie

Chakravarty

Lee

(2024). EduMAS: A novel LLM-powered multi-agent framework for educational support. In 2024 IEEE International Conference on Big Data (BigData) (pp. 8309–8316). IEEE. https://doi.org/10.1109/BigData62323.2024.10826103

25.

Cheng

Zhu

Xiong

(2023). Large language models are not stable recommender systems. arXiv preprint arXiv:2312.15746.

26.

Mishra

Warr

Islam

(2023). TPACK in the age of ChatGPT and Generative AI. Journal of Digital Learning in Teacher Education, 39(4), 235–251. https://doi.org/10.1080/21532974.2023.2247480

27.

National Center for Education Statistics. (2021). National Teacher and Principal Survey (NTPS), Public School Teacher Data File, 2020–21. U.S. Department of Education, Institute of Education Sciences. https://nces.ed.gov/surveys/ntps/estable/table/ntps/ntps2021_sflt07_t1s

28.

National Center for Education Statistics. (2024). Students with disabilities. Condition of Education. U.S. Department of Education, Institute of Education Sciences. https://nces.ed.gov/programs/coe/indicator/cgg

29.

Ocumpaugh

Roscoe

R. D.

Baker

R. S.

Hutt

Aguilar

S. J.

(2024). Toward asset-based instruction and assessment in Artificial Intelligence in Education. International Journal of Artificial Intelligence in Education, 1–40. https://doi.org/10.1007/s40593-023-00382-x

30.

OpenAI. (n.d.). Introducing OpenAI o1. https://openai.com/o1/

31.

Plass

J. L.

Pawar

(2020). Toward a taxonomy of adaptivity for learning. Journal of Research on Technology in Education, 52(3), 275–300. https://doi.org/10.1080/15391523.2020.1719943

32.

Pugach

M. C.

Matewos

A. M.

Gomez-Najarro

(2021). Disability and the meaning of social justice in teacher education research: A precarious guest at the table? Journal of Teacher Education, 72(2), 237–250. https://doi.org/10.1177/0022487120929623

33.

Redding

(2013). Through the student’s eyes: A perspective on personalized learning and practice guide for teachers. Center on Innovations in Learning. https://files.eric.ed.gov/fulltext/ED558042.pdf

34.

Rosson

M. B.

Carroll

J. M.

(2007). Scenario-based design. In Sears

Jacko

J. A.

(Eds.), The human-computer interaction handbook (pp.1067–1086). CRC Press.

35.

Roth

W. M.

Lee

Y. J.

(2007). “Vygotsky’s neglected legacy”: Cultural-Historical Activity Theory. Review of Educational Research, 77(2), 186–232. https://doi.org/10.3102/0034654306298273

36.

Rowan

Bourke

L’Estrange

Lunn Brownlee

Ryan

Walker

Churchward

(2021). How does initial teacher education research frame the challenge of preparing future teachers for student diversity in schools? A systematic review of literature. Review of Educational Research, 91(1), 112–158. https://doi.org/10.3102/0034654320979171

37.

Sahoo

Singh

A. K.

Saha

Jain

Mondal

Chadha

(2024). A systematic survey of prompt engineering in large language models: Techniques and applications. arXiv preprint arXiv:2402.07927.

38.

Schneider

Artelt

(2010). Metacognition and mathematics education. ZDM, 42, 149–161. https://doi.org/10.1007/s11858-010-0240-2

39.

Solano-Campos

Hopkins

Quaynor

(2020). Linguistically responsive teaching in preservice teacher education: A review of the literature through the lens of cultural-historical activity theory. Journal of Teacher Education, 71(2), 203–217. https://doi.org/10.1177/0022487118808785

40.

Stansberry Brusnahan

L. L.

Harkins Monaco

E. A.

Fuller

Dixon

. (2023). Diversity, equity, and inclusion: Teaching intersectional self-determination skills with a focus on disability, social identity, and culture. Teaching Exceptional Children, 55(5), 324–336. https://doi.org/10.1177/00400599231155587

41.

TeachingWorks. (n.d.). High-leverage practices. TeachingWorks Curriculum Resource Library. https://library.teachingworks.org/curriculum-resources/high-leverage-practices/

42.

Thomas

D. R.

Gatz

Gupta

Aleven

Koedinger

K. R.

(2024). The neglected 15%: Positive effects of hybrid human-AI tutoring among students with disabilities. In Olney

A. M.

Chounta

I. A.

Liu

Santos

O. C.

Bittencourt

I. I.

(Eds.), Artificial intelligence in education. AIED 2024.Lecture Notes in Computer Science (Vol. 14829). Springer, Cham. https://doi.org/10.1007/978-3-031-64302-6_29

43.

Trent

S. C.

Artiles

A. J.

Fitcbett-Bazemore

McDaniel

Coleman-Sorrell

(2002). Addressing theory ethics, power, and privilege in inclusion research and practice. Teacher Education and Special Education, 25(1), 11–22. https://doi.org/10.1177/088840640202500103

44.

van Dis

E. A.

Bollen

Zuidema

van Rooij

Bockting

C. L

. (2023). ChatGPT: Five priorities for research. Nature, 614(7947), 224–226.

45.

Vygotsky

L. S.

(1978). Mind in society: The development of higher psychological processes. Harvard University Press.

46.

Waitoller

F. R.

Kozleski

E. B.

(2013). Working in boundary practices: Identity and learning in partnerships for inclusive education. Teaching and Teacher Education, 31(1), 35–45. https://doi.org/10.1016/j.tate.2012.11.006

47.

Walkington

Bernacki

M. L.

(2020). Appraising research on personalized learning: Definitions, theoretical alignment, advancements, and future directions. Journal of Research on Technology in Education, 52(3), 235–252. https://doi.org/10.1080/15391523.2020.1747757

48.

Wehmeyer

M. L.

(2022). From segregation to strengths: A personal history of special education. Phi Delta Kappan, 103(6), 8–13. https://doi.org/10.1177/00317217221082792

49.

White

Hays

Sandborn

Olea

Gilbert

. . .Schmidt

D. C.

(2023). A prompt pattern catalog to enhance prompt engineering with ChatGPT. arXiv preprint, arXiv:2302.11382. https://doi.org/10.48550/arXiv.2302.11382

50.

Xie

Chu

H. C.

Hwang

G. J.

Wang

C. C.

(2019). Trends and development in technology-enhanced adaptive/personalized learning: A systematic review of journal publications from 2007 to 2017. Computers & Education, 140, 103599. https://doi.org/10.1016/j.compedu.2019.103599

51.

Yamagata-Lynch

L. C.

(2007). Confronting analytical dilemmas for understanding complex human interactions in design-based research from a cultural—historical activity theory (CHAT) framework. The Journal of the Learning Sciences, 16(4), 451–484. https://doi.org/10.1080/10508400701524777

52.

Yang

Carter

R. A.

Jr. Zhang

Emerling

R. C.

Hunt

T. L.

(2021). A path forward: professional development as a means to support personalised learning. Journal of Education for Teaching. https://doi.org/10.1080/02607476.2021.1885286

53.

Yao

Zhao

Shafran

Narasimhan

Cao

(2022). React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629.

54.

Yuan

Song

Chen

Tan

Shen

Kan

. . .Yang

(2024). Easytool: Enhancing LLM-based agents with concise tool instruction. arXiv preprint arXiv:2401.06201.

55.

Zeichner

K. M.

Liston

D. P.

(2013). Reflective teaching: An introduction. Routledge.

56.

Zhang

Basham

J. D.

Yang

(2020). Understanding the implementation of personalized learning: A research synthesis. Educational Research Review, 33. https://doi.org/10.1016/j.edurev.2020.100339

57.

Zhang

Carter

R. A.

Jr. Bloom

Kennett

Hoekstra

N. J.

Goldman

Rujimora

(2024). Are pre-service educators prepared to implement personalized learning? An alignment analysis of educator preparation standards. Journal of Teacher Education, 75(2), 219-235. https://doi.org/10.1177/002248712312013

58.

Zhang

Diliberto

Carter

R.A.

(in press). Understanding personalization and individualization from education policy perspectives: Towards an integrated school-wide implementation system. In Bernacki

Walkington

Emery

Zhang

(Eds.), The Handbook of Personalized Learning. Routledge.

59.

Zhang

Jackson

H. A.

Yang

Qian

Diliberto

Carter

R. A.

Jr. Zhang

. (under review). Prototyping a multi-agent system to enhance AI-human collaboration in IEP development. https://doi.org/10.21203/rs.3.rs-5339247/v1 (preprint)

60.

Zheng

Long

Zhong

Gyasi

J. F.

(2022). The effectiveness of technology-facilitated PL on learning achievements and learning perceptions: A meta-analysis. Education and Information Technologies, 1–24. https://doi.org/10.1007/s10639-022-11092-7

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.02 MB

0.45 MB

0.03 MB

3.92 MB