Generative AI in Physics Education: A PRISMA-Guided Systematic Review of Empirical Studies
Abstract
Generative artificial intelligence (GenAI) tools are redefining education, particularly in science disciplines such as physics. Even though these systems are widely used, there are still only a few studies that clearly summarize their use in teaching and their impact. In this PRISMA-guided systematic review, we analyzed 21 empirical studies (from 2023 to 2025) on the role of GenAI in physics education. We combined bibliometric mapping with content-based refinement and classified the studies by educational level, tools used, research methodology, and pedagogical role. Three main functions were identified: problem solver (57% of studies), student’s tutor (38%), and teacher’s assistant (33%). Problem-solving roles demonstrated variable accuracy, ranging from 100% to 0% across task types. Tutoring roles, though few, showed the strongest evidence of positive learning outcomes. Assistant roles mainly supported efficiency in grading and content generation, with less direct evidence of learning outcomes. The review contributes by providing this physics-specific PRISMA synthesis of GenAI in education and by identifying the roles GenAI tools assume in this context. This research is limited by the small, diverse set of included studies, which focus mainly on university contexts, and by its reliance on Scopus-indexed literature. Our findings suggest that GenAI tools can potentially improve conceptual understanding, formative assessment, and instructional efficiency. However, their…
How strong is the evidence?
Evidence Hub reads this as a systematic review. Its evidence level is 1 of 5 (Highest · pooled evidence). Pooled evidence from several studies sits at the top of the evidence pyramid.
Read the paper
Related studies
- Quantum dots: synthesis, bioapplications, and toxicity
- A Guide to In Silico Drug Design
- Quantum Computing for Healthcare: A Review
- Automated in Silico Design of Homogeneous Catalysts
- Identification of Novel 3-Hydroxy-pyran-4-One Derivatives as Potent HIV-1 Integrase Inhibitors Using in silico Structure-Based Combinatorial Library Design Approach
- In silico structural elucidation of RNA-dependent RNA polymerase towards the identification of potential Crimean-Congo Hemorrhagic Fever Virus inhibitors
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.