<![CDATA[The exploration of physics learning using an adaptive artificial intelligence–based virtual universe simulation model represents an important aspect of physics education due to the limitations of conventional instruction in visualizing abstract and multiscale physical phenomena. This challenge highlights the need for experimental research that empirically examines the effectiveness of adaptive virtual simulation models in improving students’ conceptual understanding of physics. This study aims to analyze the impact of implementing an adaptive artificial intelligence–based virtual universe simulation on students’ conceptual understanding and learning engagement in school physics. The research employed an experimental method with a quasi-experimental design involving an experimental group and a control group. Data were collected through conceptual understanding tests, learning activity observation sheets, and student engagement questionnaires. The collected data were analyzed using descriptive statistics and independent samples t-tests. The results indicate that students who learned through adaptive virtual simulations achieved a statistically significant improvement in conceptual understanding scores (p < 0.05), with an average increase of more than 20% compared to the control group. These findings suggest that adaptive virtual universe simulation–based physics learning is effective in enhancing the quality of physics instruction. This study contributes to the development of intelligent technology-based physics learning models and provides empirical evidence supporting the integration of artificial intelligence in science education.]]>
