Human-AI collaborative problem solving in middle school mathematics: an orchestration and learning review

Abstract

Artificial intelligence, particularly generative AI, is increasingly positioned as an active participant in learning rather than a passive digital tool. This systematic literature review synthesizes evidence on human-AI collaborative problem solving in mathematics, with particular attention to AI roles, collaboration patterns, learning outcomes, and pedagogical orchestration. The review followed PRISMA 2020. A Scopus title-abstract-keyword search produced 369 source records; after 10 duplicates were removed, 359 records were screened, 125 full-text reports were assessed, and 10 studies were retained for qualitative synthesis. Because the original screening archive did not preserve reviewer-level decision logs, inter-rater agreement coefficients could not be retrospectively computed without reconstruction; this limitation and a prescribed dual-reviewer rerun protocol are reported explicitly. The synthesis identified four recurring AI roles: adaptive scaffold/tutor, cognitive or visualization tool, co-creative partner, and orchestration platform. Productive collaboration was most consistently associated with socially structured routines, shared agency, reflective activity, and explicit teacher orchestration, whereas unstructured use increased the risk of cognitive off-loading and over-delegation. Learning gains were reported for problem solving, conceptual understanding, motivation, self-efficacy, and related outcomes, but causal evidence remains limited by heterogeneous designs, levels, and measures. The review therefore treats orchestration—not model capability alone—as the principal design mechanism and recommends preregistered, longitudinal, middle-school studies with process-level measures, independent dual screening, and multi-database searching.

Keywords
  • Human–AI collaboration, Artificial intelligence in education, Collaborative problem solving, Mathematics education, Pedagogical design
Lisensing Information
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

References
  1. Adiansha, A. A., Asriyadin, A., & Fauzi, A. (2026). Brain-Based Deep Learning Model Assisted By Geogebra To Enhance Mathematical Problem-Solving Skills Of Prospective Elementary School Teachers. International Journal Of Information And Education Technology, 16(6), 1662-1676. Https://Doi.Org/10.18178/Ijiet.2026.16.6.2631
  2. Albadarin, Y., Saqr, M., Pope, N., & Tukiainen, M. (2024). A Systematic Literature Review Of Empirical Research On Chatgpt In Education. Discover Education, 3, Article 60. Https://Doi.Org/10.1007/S44217-024-00138-2
  3. Albar, M., Masitoh, S., Kristanto, A., & Rajiman, W. (2025). Effect Of Google Sites-Assisted Flipped Classroom Discovery Learning Model And Cognitive Style On Mathematics Problem-Solving Skills And Student Learning Independence. Ianna Journal Of Interdisciplinary Studies, 7(2), 236-249. Https://Doi.Org/10.5281/Zenodo.15462037
  4. Ali, A., Khusro, S., & Alahmadi, T. J. (2024). Accessible Interactive Learning Of Mathematical Expressions For School Students With Visual Disabilities. Peerj Computer Science, 10. Https://Doi.Org/10.7717/Peerj-Cs.2599
  5. Anwar, L., Sa’dijah, C., Cahyowati, E. T. D., & Zahroh, I. E. P. (2026). Critical Thinking In Mathematics Education: A Prisma-Based Systematic Review. Social Sciences And Humanities Open, 14. Https://Doi.Org/10.1016/J.Ssaho.2026.103284
  6. Aydin, U., & Ubuz, B. (2010). Turkish Version Of The Junior Metacognitive Awareness Inventory: The Validation Study. Education And Science, 35(157), 30–45. Https://Doi.Org/10.15390/Es.2010.874
  7. Canonigo, A. M. (2024). Levering Ai To Enhance Students' Conceptual Understanding And Confidence In Mathematics. Journal Of Computer Assisted Learning, 40(6), 3215-3229. Https://Doi.Org/10.1111/Jcal.13065
  8. Castillo, E. R., León, J. A. M., Celiz, E. B., Alarcón, T. J. J., & Del Milagro Chunga More, Y. (2025). Technological Tools Used In Mathematical Thinking At The University Level: A Systematic Review. Journal Of Educational And Social Research, 15(2), 73-84. Https://Doi.Org/10.36941/Jesr-2025-0043
  9. Chan, M. C. E. (2026). Using Multimodal Learning Analytics To Study Student Engagement And Teacher Noticing In Mathematics Classroom: Two Different Human-In-The-Loop Workflows. Zdm - Mathematics Education. Https://Doi.Org/10.1007/S11858-026-01809-0
  10. Chan, M. C. E. (2026). Using Multimodal Learning Analytics To Study Student Engagement And Teacher Noticing In Mathematics Classroom: Two Different Human-In-The-Loop Workflows. Zdm – Mathematics Education. Https://Doi.Org/10.1007/S11858-026-01809-0
  11. Chen, L., Taniguchi, Y., Shimada, A., & Yamada, M. (2024). Exploring Behavioral And Strategic Factors Affecting Secondary Students’ Learning Performance In Collaborative Problem Solving-Based Stem Lessons. Sage Open, 14(2). Https://Doi.Org/10.1177/21582440241251641
  12. Choi, W. Y. (2026). Integrating Generative Ai In University Mathematics: Reflective And Collaborative Learning As Pedagogical Safeguards. Education And Information Technologies, 31(11), 3925-3946. Https://Doi.Org/10.1007/S10639-026-13945-X
  13. Cirneanu, A. L., & Moldoveanu, C. E. (2024). Use Of Digital Technology In Integrated Mathematics Education. Applied System Innovation, 7(4). Https://Doi.Org/10.3390/Asi7040066
  14. Demir, B., Çanakçi, E., Düzgün, F. N., Çam, M., & Beyazhançer, R. (2025). Self-Regulation Scale In Mathematics: Short Form Development And Validity-Reliability Study. Journal For The Mathematics Education And Teaching Practices, 6(1).
  15. Deng, R., Jiang, M., Yu, X., Lu, Y., & Liu, S. (2024). Does Chatgpt Enhance Student Learning? A Systematic Review And Meta-Analysis Of Experimental Studies. Computers & Education, 219, 105224. Https://Doi.Org/10.1016/J.Compedu.2024.105224
  16. Edson, A. J., Fabry, A., Kohar, A. W., Bondaryk, L., & Phillips, E. D. (2025). Addressing Design Challenges When Integrating Machine Learning With A Digital Annotation System To Examine Student Proportional Reasoning. Digital Experiences In Mathematics Education, 11(1), 42-76. Https://Doi.Org/10.1007/S40751-024-00163-8
  17. Elnaffar, S., & Fawey, M. (2024). Uncovering The Most Effective Pedagogical Techniques For Math Education Using Machine Learning. International Journal On Informatics Visualization, 8(3-2), 1671-1677. Https://Doi.Org/10.62527/Joiv.8.3-2.3123
  18. Fang, J. W., Guo, X. G., Meng, X. P., Hwang, G. J., & Tu, Y. F. (2026). Realization Of Parasocial Interaction Theory In Steam Education With An Ai Pedagogical Agent: Insights From Learning Performance, Collaboration Tendency, And Problem-Solving Tendency. Interactive Learning Environments, 34(2), 694-717. Https://Doi.Org/10.1080/10494820.2025.2508326
  19. Gawlik-Kobylińska, M. (2024). Harnessing Artificial Intelligence For Enhanced Scientific Collaboration: Insights From Students And Educational Implications. Education Sciences, 14(10). Https://Doi.Org/10.3390/Educsci14101132
  20. Guerino, G., Rodrigues, L., Bianchini, L., Alves, M., Marinho, M., Veloso, T., Macario, V., Dermeval, D., Vieira, T., Bittencourt, I., & Isotani, S. (2026). A Mixed User-Centered Approach To Enable Augmented Intelligence In Intelligent Tutoring Systems: The Case Of Mathaide App. International Journal Of Human-Computer Interaction, 42(8), 6558-6580. Https://Doi.Org/10.1080/10447318.2025.2553778
  21. Hamsiah, A., Rizal, A., & Malik, A. R. (2026). Chatgpt Use In Higher Education Writing And Its Relationship With Critical Thinking Autonomy Struggle And Authorship. Discover Education, 5(1). Https://Doi.Org/10.1007/S44217-026-01627-2
  22. Hariyanti, F., Budayasa, I. K., & Setianingsih, R. (2025). The Role Of Ai In Enhancing Statistical Literacy: A Systematic Review In Education. Multidisciplinary Reviews, 8(12). Https://Doi.Org/10.31893/Multirev.2025376
  23. Hunt, T., Zhang, L., Sanders, M., Joswick, C., & Nelson, J. (2026). Collaborative Design: Leveraging Genai To Create Metacognition-Aligned Mathematics Instruction For Students With Disabilities. Journal Of Special Education Technology. Https://Doi.Org/10.1177/01626434261435266
  24. Ji, Y., Zhan, Z., Li, T., Zou, X., & Lyu, S. (2025). Human-Machine Cocreation: The Effects Of Chatgpt On Students' Learning Performance, Ai Awareness, Critical Thinking, And Cognitive Load In A Stem Course Toward Entrepreneurship. Ieee Transactions On Learning Technologies, 18, 402-415. Https://Doi.Org/10.1109/Tlt.2025.3554584
  25. Juan, Y. C., Lee, Y. H., & Wu, J. Y. (2026). Generative Artificial Intelligence Augments Social Interactivity And Learning Outcomes: Advancing The Framework Of A Scaffolded Human–Genai Shared Agency. Computers And Education, 247. Https://Doi.Org/10.1016/J.Compedu.2026.105564
  26. Kassanew, B., Weng, C., Astatke, M., & Kassanew, Y. (2026). The Impact Of Ai-Supported Think-Pair-Share Instruction On Students' Problem-Solving Skills And Motivation In Learning Quadratic Equations: A Social Constructivist Perspective. Journal Of Computer Assisted Learning, 42(4). Https://Doi.Org/10.1002/Jcal.70271
  27. Khaleghi, E., & Rayner, R. (2025). Revolutionising Education Through Digital Twins: Case Study And Applications. Mechatronic Futures: Further Challenges And Solutions For Mechatronic Systems And Their Designers, 393-414. Https://Doi.Org/10.1007/978-3-031-83571-1_21
  28. Lee, J. (2025). Empowering Students Through Generative Ai And Cultural Diversity In Interdisciplinary Fashion Design Education. Research Journal Of Textile And Apparel. Https://Doi.Org/10.1108/Rjta-02-2025-0017
  29. Lin, D., Shuang, X., & Zongben, X. (2025). Teacher-Student-Ai Collaborative Classroom: The Platform And Practice Of Ai-Empowered University Mathematics Education. Frontiers Of Education In China, 20(4), 477-489. Https://Doi.Org/10.3868/S110-020-025-0025-8
  30. Lingling, W., Shijie, S., & Xueyi, L. (2026). From Automation To Augmentation: A Retrieval-Augmented Large Language Model Framework For Reshaping Learning Experiences In Higher Education. Frontiers In Psychology, 17. Https://Doi.Org/10.3389/Fpsyg.2026.1870870
  31. Listyaningrum, P., Retnawati, H., Harun, & Ibda, H. (2024). Digital Learning Using Chatgpt In Elementary School Mathematics Learning: A Systematic Literature Review. Indonesian Journal Of Electrical Engineering And Computer Science, 36(3), 1701-1710. Https://Doi.Org/10.11591/Ijeecs.V36.I3.Pp1701-1710
  32. López-Goyez, J. P., González-Briones, A., & Demazeau, Y. (2026). An Adaptive Multi-Agent Architecture With Reinforcement Learning And Generative Ai For Intelligent Tutoring Systems: A Moodle-Based Case Study. Applied Sciences (Switzerland), 16(3). Https://Doi.Org/10.3390/App16031323
  33. Luo, X., Wang, S., & Hew, K. F. (2026). Equipping Elementary School Students With Self-Regulated Learning Through Human-Ai Collaboration In Online Learning. Computers And Education, 253. Https://Doi.Org/10.1016/J.Compedu.2026.105697
  34. Maalek, R. (2024). Integrating Generative Artificial Intelligence And Problem-Based Learning Into The Digitization In Construction Curriculum. Buildings, 14(11). Https://Doi.Org/10.3390/Buildings14113642
  35. Martinez, J. A. (2025). The New Era Of Artificial Intelligence: Empowering Coders, Non-Coders, And Shaping Future Workforce Creativity. Ai, Personalization, Equity, And The Future Of Learning, 139-158. Https://Doi.Org/10.4018/979-8-3373-5097-4.Ch005
  36. Marzano, D. (2025). Generative Artificial Intelligence (Gai) In Teaching And Learning Processes At The K-12 Level: A Systematic Review. Technology, Knowledge And Learning, 31, 789–829. Https://Doi.Org/10.1007/S10758-025-09853-7
  37. Otto, S., Ejsing-Duun, S., & Lindsay, E. (2025a). Disruptive Tensions And Emerging Practices: An Exploratory Inquiry Into Student Perspectives On Generative Artificial Intelligence In A Problem-Based Learning Environment. Education And Information Technologies, 30(13), 19111-19140. Https://Doi.Org/10.1007/S10639-025-13533-5
  38. Otto, S., Lavi, R., & Brogaard Bertel, L. (2025b). Human-Genai Interaction For Active Learning In Stem Education: State-Of-The-Art And Future Directions. Computers And Education, 239. Https://Doi.Org/10.1016/J.Compedu.2025.105444
  39. Oviatt, S., & Cohen, A. (2014). Written Activity, Representations And Fluency As Predictors Of Domain Expertise In Mathematics. Icmi 2014 - Proceedings Of The 2014 International Conference On Multimodal Interaction, 10-17. Https://Doi.Org/10.1145/2663204.2663245
  40. Oviatt, S., Hang, K., Zhou, J., & Chen, F. (2015). Spoken Interruptions Signal Productive Problem Solving And Domain Expertise In Mathematics. Icmi 2015 - Proceedings Of The 2015 Acm International Conference On Multimodal Interaction, 311-318. Https://Doi.Org/10.1145/2818346.2820743
  41. Pirker, J., Riffnaller-Schiefer, M., & Gütl, C. (2014). Motivational Active Learning - Engaging University Students In Computer Science Education. Iticse 2014 - Proceedings Of The 2014 Innovation And Technology In Computer Science Education Conference, 297-302. Https://Doi.Org/10.1145/2591708.2591750
  42. Renjewski, D., & Strasser, A. (2026). Designing Ai-Resilient Exams: Error-Correction Assignments In Engineering Education. Human-Centric Intelligent Systems. Https://Doi.Org/10.1007/S44230-026-00157-2
  43. Shi, K., Yang, Y., Liang, T., Zhang, L., Zhao, Z., & Hu, C. (2026). Umath: Closing The Loop Between Student Ai Tutoring And Teacher Insight In Mathematics. Ieee Global Engineering Education Conference, Educon. Https://Doi.Org/10.1109/Educon67543.2026.11574145
  44. Stamenkova, R. (2025). Large Language Models: A Tool For Solving Mathematical Problems In High School. Annual Of Sofia University "St. Kliment Ohridski" Faculty Of Mathematics And Informatics, 112, 165-183. Https://Doi.Org/10.60063/Gsu.Fmi.112.165-183
  45. Tassilova, N. A., Shashayeva, G. K., Yernazarova, Z. S. H., Akhmetova, A. I., Arynov, Z. M., & Karimova, Z. K. (2025). Communication Technologies In Stem Education: A Systematic Review. Eurasia Journal Of Mathematics, Science And Technology Education, 21(10). Https://Doi.Org/10.29333/Ejmste/17178
  46. Tu, Y. F., Guo, X. G., Fang, J. W., Meng, X. P., & Hwang, G. J. (2026). Roles And Impacts Of Generative Ai Agents In Steam Learning: Insights From Students’ Perceptions And Learning Experiences Using Information World Mapping. Educational Technology Research And Development, 74(2), 897-935. Https://Doi.Org/10.1007/S11423-025-10579-7
  47. Turmuzi, M., Azmi, S., & Kertiyani, N. M. I. (2026). Chatgpt In School Mathematics Education: A Systematic Review Of Opportunities, Challenges, And Pedagogical Implications. Teaching And Teacher Education, 170, 105286. Https://Doi.Org/10.1016/J.Tate.2025.105286
  48. Wong, K., Bulathwela, S., & Cukurova, M. (2026). Towards An Adaptive Ai Scaffold For Developing Student Collaborative Problem Solving. Learning And Instruction, 105. Https://Doi.Org/10.1016/J.Learninstruc.2026.102418
  49. Yildiz, S. G., & Körpeoğlu, S. G. (2025). Trends And Insights Of Ai In Mathematics Education: A Bibliometric Analysis. International Electronic Journal Of Mathematics Education, 20(3). Https://Doi.Org/10.29333/Iejme/16401
  50. Zhang, D., Wijaya, T. T., Wang, Y., Su, M., Li, X., & Damayanti, N. W. (2025). Exploring The Relationship Between Ai Literacy, Ai Trust, Ai Dependency, And 21st Century Skills In Preservice Mathematics Teachers. Scientific Reports, 15(1). Https://Doi.Org/10.1038/S41598-025-99127-0
  51. Zhang, H., Xiao, X., & Zhang, J. (2026a). The Impact Of Artificial Intelligence Literacy On Students' Social-Emotional Competence: An Empirical Study Using Random Forest Feature Importance Modeling. Proceedings Of 2025 3rd International Conference On Information Education And Artificial Intelligence, Icieai 2025, 546-551. Https://Doi.Org/10.1145/3799457.3799547
  52. Zhang, M., Raytchev, B., & Sun, X. (2026b). Realm: A Relevance-Driven Layered Protocol For Human–Ai Collaboration In Stem Education. Ieee Signal Processing Magazine, 43(1), 56-68. Https://Doi.Org/10.1109/Msp.2025.3599339

Downloads

PDF

Statistic

Abstract Views
: 9 times
PDF
: 3 times