Research Article

The design and impact of a dual-agent artificial intelligence system in personalised mathematics tutoring

Ruonan Wang 1 * , Laura Tuohilampi 2
More Detail
1 School of Mathematics and Statistics, The University of New South Wales, Sydney, NSW, AUSTRALIA2 School of Education, The University of New South Wales, Sydney, NSW, AUSTRALIA* Corresponding Author
Contemporary Educational Technology, 18(4), October 2026, ep704, https://doi.org/10.30935/cedtech/19950
Published: 14 November 2026
OPEN ACCESS   35 Views   22 Downloads
Download Full Text (PDF)

ABSTRACT

Digital tutoring tools are increasingly used in schools to support mathematics learning, but empirical evidence remains limited on how diagnostic and instructional functions can be coordinated to provide personalised support. This study examined a dual-agent intervention in which a diagnostic agent generated provisional learning-profile classifications (diverging, assimilating, converging, and accommodating) and a personalised tutoring agent delivered profile-responsive, stage-specific guidance within Polya’s (1945) problem-solving framework; a general tutoring agent provided non-profile-responsive guidance in the control condition. The quasi-experimental study involved 206 Chinese grade 5 students, including 99 in the experimental group and 107 in the control group. The pre-test and post-test used two parallel mathematics tasks evaluated using the same analytic rubric, and learning gain was calculated from these matched assessment components. The experimental group achieved a significantly larger mean gain than the control group (5.14 vs. 0.94, t(204) = 4.36, p < .001, Hedges’ g = .61). A baseline-adjusted sensitivity analysis confirmed the overall group effect (p < .001). After Holm correction for four profile-specific comparisons, only the assimilating-profile contrast remained significant (adjusted p = .0496). However, the omnibus group-by-profile interaction was not significant (p = .931), warranting caution in interpreting profile-specific differences. Overall, the findings support separating diagnostic and tutoring roles and structuring artificial intelligence (AI) guidance around mathematical problem-solving stages.
Keywords: learning profiles, pedagogical AI agents, personalised mathematical tutoring, Polya’s problem-solving model, quasi-experimental design

CITATION (APA)

Wang, R., & Tuohilampi, L. (2026). The design and impact of a dual-agent artificial intelligence system in personalised mathematics tutoring. Contemporary Educational Technology, 18(4), ep704. https://doi.org/10.30935/cedtech/19950

REFERENCES

  1. Akbulut, Y., & Cardak, C. S. (2012). Adaptive educational hypermedia accommodating learning styles: A content analysis of publications from 2000 to 2011. Computers & Education, 58(2), 835-842. https://doi.org/10.1016/j.compedu.2011.10.008
  2. Apoki, U. C., Hussein, A. M. A., Al-Chalabi, H. K. M., Badica, C., & Mocanu, M. L. (2022). The role of pedagogical agents in personalised adaptive learning: A review. Sustainability, 14(11), Article 6442. https://doi.org/10.3390/su14116442
  3. Calderón Carvajal, C., Ximénez Gómez, C., Lay-Lisboa, S., & Briceño, M. (2021). Reviewing the structure of Kolb’s learning style inventory from factor analysis and Thurstonian item response theory (IRT) model approaches. Journal of Psychoeducational Assessment, 39(5), 593-609. https://doi.org/10.1177/07342829211003739
  4. Dewey, J. (1916). Democracy and education: An introduction to the philosophy of education. Macmillan.
  5. Dookurong, I. D., Yarhands, D. A., & Akwerty, E. (2025). A systematic review of the integration of collaborative learning and Polya’s problem-solving strategy for enhancing pre-service teachers’ critical thinking. International Journal of Studies in Education and Science, 6(4), 395-428. https://doi.org/10.46328/ijses.5520
  6. Engelbrecht, J., & Borba, M. C. (2024). Recent developments in using digital technology in mathematics education. ZDM Mathematics Education, 56, 281-292. https://doi.org/10.1007/s11858-023-01530-2
  7. Gašević, D., Siemens, G., & Sadiq, S. (2023). Empowering learners for the age of artificial intelligence. Computers and Education: Artificial Intelligence, 4, Article 100130. https://doi.org/10.1016/j.caeai.2023.100130
  8. Gibson, D., Kovanovic, V., Ifenthaler, D., Dexter, S., & Feng, S. (2023). Learning theories for artificial intelligence promoting learning processes. British Journal of Educational Technology, 54(5), 1125-1146. http://doi.org/10.1111/bjet.13341
  9. Han, Y., Hong, S., Li, Z., & Lim, C. (2025). Defining and classifying the roles of intelligent learning companion systems: A scoping review of the literature. TechTrends, 69(3), 567-581. https://doi.org/10.1007/s11528-025-01058-0
  10. Hong, X., & Guo, L. (2025). Effects of AI-enhanced multi-display language teaching systems on learning motivation, cognitive load management, and learner autonomy. Education and Information Technologies, 30(12), 17155-17189. https://doi.org/10.1007/s10639-025-13472-1
  11. Huertas, A., López, O., & Sanabria, L. (2017). Influence of a metacognitive scaffolding for information search in b-learning courses on learning achievement and its relationship with cognitive and learning style. Journal of Educational Computing Research, 55(2), 147-171. https://doi.org/10.1177/0735633116656634
  12. Hwang, G.-J., Sung, H.-Y., Hung, C.-M., Huang, I., & Tsai, C.-C. (2012). Development of a personalized educational computer game based on students’ learning styles. Educational Technology Research and Development, 60(4), 623-638. https://doi.org/10.1007/s11423-012-9241-x
  13. Jyrwa, K., & May, S. (2025). Learning difficulties and remedial teaching in mathematics: Insights and interventions for educators. The Online Journal of Distance Education and e-Learning, 13(1), 16-18. https://www.tojdel.net/journals/tojdel/volumes/tojdel-volume13-i01.pdf
  14. Kolb, D. A. (2014). Experiential learning: Experience as the source of learning and development (2nd ed.). FT Press.
  15. Lai, L., She, L., & Li, C. (2024). Online teaching model in the context of blended learning environment: Experiential learning and TAM. Education and Information Technologies, 29(13), 17235-17259. https://doi.org/10.1007/s10639-024-12465-w
  16. Lee, C. I. (2017). An appropriate prompts system based on the Polya method for mathematical problem-solving. Eurasia Journal of Mathematics, Science and Technology Education, 13(3), 893-910. https://doi.org/10.12973/eurasia.2017.00649a
  17. Lin, C.-J., Lee, H.-Y., Wang, W.-S., Huang, Y.-M., & Wu, T.-T. (2025). Enhancing reflective thinking in STEM education through experiential learning: The role of generative AI as a learning aid. Education and Information Technologies, 30(5), 6315-6337. https://doi.org/10.1007/s10639-024-13072-5
  18. López-Mendoza, A., Roque-Hernández, R. V., & Salazar-Hernández, R. (2026). Adoption and use of ChatGPT among university IT students: An exploratory study. Contemporary Educational Technology, 18(1), Article ep624. https://doi.org/10.30935/cedtech/17864
  19. Mahmud, M. S., & Mohd Drus, N. F. (2023). The use of oral questioning to improve students’ reasoning skills in primary school mathematics learning. Frontiers in Education, 8, Article 1126816. https://doi.org/10.3389/feduc.2023.1126816
  20. Ministry of Education of the People’s Republic of China. (2022). Yiwu jiaoyu shuxue kecheng biaozhun (2022 nian ban) [Mathematics curriculum standards for compulsory education (2022 edition)]. Beijing Normal University Press.
  21. Mohamed, M. Z. B., Hidayat, R., Suhaizi, N. N. B., Sabri, N. B. M., Mahmud, M. K. H. B., & Baharuddin, S. N. B. (2022). Artificial intelligence in mathematics education: A systematic literature review. International Electronic Journal of Mathematics Education, 17(3), Article em0694. https://doi.org/10.29333/iejme/12132
  22. Muhamad Fadzil, N., Osman, S., Ahmad, J., Jambari, H., & Said Husain, S. K. (2025). Enhancing students’ problem-solving skills in algebra word problems: A systematic review of TAPPS and storyboarding strategies. International Electronic Journal of Mathematics Education, 20(4), Article em0850. https://doi.org/10.29333/iejme/16835
  23. Nasongkhla, J., & Shieh, C.-J. (2025). AI robots as learning companions in PBL: Effects on cognitive and self-regulatory outcomes. Contemporary Educational Technology, 17(4), Article ep603. https://doi.org/10.30935/cedtech/17417
  24. Oudman, S., van de Pol, J., & van Gog, T. (2022). Effects of self-scoring their math problem solutions on primary school students’ monitoring and regulation. Metacognition and Learning, 17(1), 213-239. https://doi.org/10.1007/s11409-021-09281-9
  25. Owan, V. J., Mohammed, I. A., Bello, A., & Shittu, T. A. (2025). Higher education students’ ChatGPT use behavior: Structural equation modelling of contributing factors through a modified UTAUT model. Contemporary Educational Technology, 17(4), Article ep592. https://doi.org/10.30935/cedtech/17243
  26. Polya, G. (1945). How to solve it: A new aspect of mathematical method. Princeton University Press. https://doi.org/10.1515/9781400828678
  27. Powell, W., & Kusuma-Powell, O. (2011). How to teach now: Five keys to personalized learning in the global classroom. ASCD.
  28. Primary Mathematics Textbook Editorial Committee, Curriculum and Teaching Materials Research Institute, People’s Education Press. (2022a). Yiwu jiaoyu jiaokeshu: Shuxue, si nianji, xia ce [Compulsory education textbook: Mathematics, grade 4, second semester] (2nd ed.). People’s Education Press.
  29. Primary Mathematics Textbook Editorial Committee, Curriculum and Teaching Materials Research Institute, People’s Education Press. (2022b). Yiwu jiaoyu jiaokeshu: Shuxue, wu nianji, shang ce [Compulsory education textbook: Mathematics, grade 5, first semester] (2nd ed.). People’s Education Press.
  30. Primary Mathematics Textbook Editorial Committee, Curriculum and Teaching Materials Research Institute, People’s Education Press. (2022c). Yiwu jiaoyu jiaokeshu: Shuxue, wu nianji, xia ce [Compulsory education textbook: Mathematics, grade 5, second semester] (2nd ed.). People’s Education Press.
  31. Rahmawati, D., & Anwar, R. B. (2020). Translation of mathematical representation: Characteristics of verbal representation unpacking. Journal of Education and Learning, 14(2), 162-167. https://doi.org/10.11591/edulearn.v14i2.9538
  32. Schorcht, S., Buchholtz, N., & Baumanns, L. (2024). Prompt the problem – Investigating the mathematics educational quality of AI-supported problem solving by comparing prompt techniques. Frontiers in Education, 9, Article 1386075. https://doi.org/10.3389/feduc.2024.1386075
  33. Shoustikova, T., Zaripova, Z. F., Ibragimov, G., Zaitseva, N. A., Pashanova, O. V., & Lobuteva, A. V. (2026). Exploring the scope of artificial intelligence literacy in education: A bibliometric approach. Contemporary Educational Technology, 18(1), Article ep628. https://doi.org/10.30935/cedtech/17892
  34. Singh, A., Ehtesham, A., Kumar, S., & Khoei, T. T. (2025). Agentic retrieval-augmented generation: A survey on agentic RAG. arXiv. https://arxiv.org/abs/2501.09136v1
  35. Sujatha, S., & Vinayakan, K. (2023). Engaging students with mathematics: A review of motivation and engagement strategies. International Journal of Interdisciplinary Research in Arts and Humanities, 8(2), 55-60. http://doi.org/10.5281/zenodo.16413870
  36. Tay, Y. K., & Toh, T. L. (2023). A model for scaffolding mathematical problem-solving: From theory to practice. Contemporary Mathematics and Science Education, 4(2), Article ep23019. https://doi.org/10.30935/conmaths/13308
  37. Tong, D. H., Nguyen, H. T., Nguyen, T.-T., Le, T. T. T., Vo, X. M., Triet, L. V. M., & Dung, T. M. (2026). Factors shaping teachers’ beliefs about ICT use in mathematics teaching. Contemporary Educational Technology, 18(1), Article ep629. https://doi.org/10.30935/cedtech/17893
  38. Tuohilampi, L., & Jiang, H. (2024). Introducing the ProInterest model: Designing tasks for sustainable positive mathematics experiences. LUMAT: International Journal on Math, Science and Technology Education, 12(3), Article 9. https://doi.org/10.31129/LUMAT.12.3.2373
  39. Ussenova, G., Issayeva, G., Urazaliyeva, R., Karimova, G., & Mukhanova, M. (2025). Examining cognitive independence in the context of digital learning: A moderation analysis of student motivation, self-regulation skills, and cognitive engagement. Contemporary Educational Technology, 17(4), Article ep618. https://doi.org/10.30935/cedtech/17570
  40. Valquaresma, A. (2024). Creativity, agency and meaning-making: Unfolding developmental possibilities in twenty-first-century learning environments. In A. Valquaresma, L. Dantas de Paula, & T. K. Rodney (Eds.), Creativity and learning: Navigating transformative perspectives for complex and contemporary environments (pp. 105-126). Palgrave Macmillan. https://doi.org/10.1007/978-3-031-73393-2_5
  41. Wu, Y., Jiang, Y., Chen, Y., & Zhang, W. (2024). Da yuyan moxing zhichi de duozhinengti: Jishu lujing, jiaoyu yingyong yu weilai zhanwang [Multi-agent systems supported by large language models: Technical pathways, educational applications, and future prospects]. Open Education Research, 30(5), 77-89. https://doi.org/10.13966/j.cnki.kfjyyj.2024.05.007
  42. Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2022). ReAct: Synergizing reasoning and acting in language models [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2210.03629
  43. Zhang, Z., Yao, Y., Zhang, A., Tang, X., Ma, X., He, Z., Wang, Y., Gerstein, M., Wang, R., Liu, G., & Zhao, H. (2025). Igniting language intelligence: The hitchhiker’s guide from chain-of-thought reasoning to language agents. ACM Computing Surveys, 57(8), Article 206. https://doi.org/10.1145/3719341