- Physical Review Journals
All JournalsPhysics Magazine

Physical Review Physics Education Research

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Editors' Suggestion
  • Open Access

Leveraging generative artificial intelligence for simulation-based physics experiments: A new approach to virtual learning about the real world

Yossi Ben-Zion1,*, Turhan K. Carroll2,*,†, Colin G. West3,*, Jesse Wong3, and Noah D. Finkelstein3

  • *These authors contributed equally to this work.
  • †Contact author: tkcarroll@uga.edu
PDF

Phys. Rev. Phys. Educ. Res. 22, 010109 – Published 26 January, 2026

DOI: https://doi.org/10.1103/s8dy-kqy5

Abstract

This study investigates the impact of a novel application of generative artificial intelligence (AI) in physics instruction: engaging students in prompting, refining, and validating AI-constructed simulations of physical phenomena. In a second-semester physics course for life science majors, we conducted a comparative study of three instructional approaches in a laboratory focused on electric potentials: (i) students using physical equipment, (ii) students using a prebuilt simulator, and (iii) students using AI to generate a simulation. Among the groups, we found significant differences in performance on conceptual assessments of the laboratory content (η2=0.359). Post hoc analysis showed that students in both the AI-generated and prebuilt simulation conditions scored significantly higher on the conceptual assessments than students in the physical equipment condition. Students in these groups also reported more favorable perceptions of the learning experience. Finally, this preliminary study highlights opportunities for developing students’ modeling skills through the processes of designing, refining, and validating AI-generated simulations.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (34)

  1. G. Kortemeyer, Could an artificial-intelligence agent pass an introductory physics course?, Phys. Rev. Phys. Educ. Res. 19, 010132 (2023).
  2. C. G. West, AI and the FCI: Can ChatGPT project an understanding of introductory physics?, arXiv:2303.01067.
  3. G. Polverini, J. Melin, E. Onerud, and B. Gregorcic, Performance of ChatGPT on tasks involving physics visual representations: The case of the brief electricity and magnetism assessment, Phys. Rev. Phys. Educ. Res. 21, 010154 (2025).
  4. G. Kestin, K. Miller, A. Klales, T. Milbourne, and G. Ponti, AI tutoring outperforms in-class active learning: An RCT introducing a novel research-based design in an authentic educational setting, Sci. Rep. 15, 17458 (2025).
  5. Y. Ben-Zion, R. E. Zarzecki, J. Glazer, and N. D. Finkelstein, Leveraging AI for rapid generation of physics simulations in education: Building your own virtual lab, Phys. Teach. 63, 424 (2025).
  6. K. T. Kotsis, ChatGPT as teacher assistant for physics teaching, EIKI J. Eff. Teach. Methods 2, 4 (2024).
  7. F. Mahligawati, E. Allanas, M. H. Butarbutar, and N. A. N. Nordin, Artificial intelligence in physics education: A comprehensive literature review, J. Phys. Conf. Ser. 2596, 012080 (2023).
  8. E. E. Ukoh and J. Nicholas, AI adoption for teaching and learning of physics, Int. J. Infonomics 15, 2121 (2022).
  9. J. Dewey, Experience and Education (Macmillan, New York, NY, 1938).
  10. N. D. Finkelstein et al., When learning about the real world is better done virtually: A study of substituting computer simulations for laboratory equipment, Phys. Rev. ST Phys. Educ. Res. 1, 1 (2005).
  11. N. M. Seel, Experimental and quasi-experimental designs for research on learning, in Encyclopedia of the Sciences of Learning (Springer, Boston, MA, 2012), pp. 1223–1229.
  12. M. Chhabra and R. Das, Conceptualization of electrostatic potential: Resource theory perspective, Phys. Educ. 60, 055019 (2025).
  13. J. P. Burde and T. Wilhelm, Teaching electric circuits with a focus on potential differences, Phys. Rev. Phys. Educ. Res. 16, 020153 (2020).
  14. D. Psillos, A. Tiberghien, and P. Koumaras, Voltage presented as a primary concept in an introductory teaching sequence on dc circuits, Int. J. Sci. Educ. 10, 29 (1988).
  15. R. Millar and K. L. Beh, Students’ understanding of voltage in simple parallel electric circuits, Int. J. Sci. Educ. 15, 351 (1993).
  16. E. Ostertagová, O. Ostertag, and J. Kováč, Methodology and application of the Kruskal-Wallis test, Appl. Mech. Mat. 611, 115 (2014).
  17. B. Efron and R. Tibshirani, Bootstrap methods for standard errors, confidence intervals, and other measures of statistical accuracy, Stat. Sci. 1, 1 (1986).
  18. J. S. Haukoos and R. J. Lewis, Advanced statistics: bootstrapping confidence intervals for statistics with “difficult” distributions, Acad. Emerg. Med. 12, 360 (2005).
  19. W. H. Kruskal and W. A. Wallis, Use of ranks in one-criterion variance analysis, J. Am. Stat. Assoc. 47, 583 (1952).
  20. J. Cohen, Statistical Power Analysis for the Behavioral Sciences, 2nd ed. (Lawrence Erlbaum Associates, Hillsdale, NJ, 1988).
  21. O. J. Dunn, Multiple comparisons using rank sums, Technometrics 6, 241 (1964).
  22. B. Van Dusen and J. M. Nissen, Criteria for collapsing rating scale responses: A case study of the class, presented at PER Conf. 2019, Provo, UT 2019, 10.1119/perc.2019.pr.Van_Dusen.
  23. A. Agresti, An Introduction to Categorical Data Analysis, 2nd ed. (John Wiley & Sons, Hoboken, NJ, 2007).
  24. N. Finkelstein, Learning physics in context: A study of student learning about electricity and magnetism, Int. J. Sci. Educ. 27, 1187 (2005).
  25. C. H. Crouch and E. Mazur, Peer instruction: Ten years of experience and results, Am. J. Phys. 69, 970 (2001).
  26. S. Freeman, S. L. Eddy, McM. Donough, M. K. Smith, N. Okoroafor, H. Jordt, and M. P. Wenderoth, Active learning increases student performance in science, engineering, and mathematics, Proc. Natl. Acad. Sci. U.S.A. 111, 8410 (2014).
  27. C. Turpen and N. D. Finkelstein, Not all interactive engagement is the same: Variations in physics professors’ implementation of peer instruction, Phys. Rev. ST Phys. Educ. Res. 5, 020101 (2009).
  28. H. Elsayed, The impact of hallucinated information in large language models on student learning outcomes: A critical examination of misinformation risks in AI-assisted education, North. Rev. Algorithm Res. Theor. Comput. Complexity 9, 8 (2024), https://northernreviews.com/index.php/NRATCC/article/view/2024-08-07.
  29. N. G. Holmes and C. E. Wieman, Introductory physics labs: We can do better, Phys. Today 71, No. 1, 38 (2018).
  30. J. Kozminski et al., AAPT Recommendations for the Undergraduate Physics Laboratory Curriculum (American Association of Physics Teachers, College Park, MD, 2014).
  31. B. R. Wilcox and H. J. Lewandowski, Students’ views about the nature of experimental physics, Phys. Rev. Phys. Educ. Res. 13, 020110 (2017).
  32. E. Etkina, A. Warren, and M. Gentile, The role of models in physics instruction, Phys. Teach. 44, 34 (2006).
  33. S. Keskin, Comparison of several univariate normality tests regarding type I error rate and power of the test in simulation based small samples, J. Appl. Sci. Res. 2, 5 (2006), https://www.academia.edu/83340328/Comparison_of_Several_Univariate_Normality_Tests_Regarding_Type_I_Error_Rate_and_Power_of_the_Test_in_Simulation_based_Small_Samples.
  34. S. S. Shapiro and M. B. Wilk, An analysis of variance test for normality (complete samples), Biometrika 52, 591 (1965).

Outline

Information

Phys. Rev. Phys. Educ. Res. 22, 010109– Published 26 January, 2026
  • Received 26 September 2025
  • Accepted 22 December 2025
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation