Artificial Intelligence as a Co-Tutor: Assessing the Impact in the Advanced Learning Virtual Classroom

Abstract

Large language models (LLMs) have the potential to impact learning in the advanced learner virtual classroom through personalized learning and on-demand feedback. This study investigated whether an LLM added to virtual science course activities impacted student learning. Using the GPT4o model from OpenAI, the LLM was developed as a co-tutor to target higher-order cognitive skills by modeling solution behavior through student–LLM interactions. A between-subjects quasi-experimental study was conducted with 22 students in 7th to 10th grades to compare differences in learning between those who completed a course with the LLM ( $M_{\mathrm{age}}=12.9,S{D}_{\mathrm{age}}=0.5,82\text{\%}$ female) and those who did not ( $M_{\mathrm{age}}=14.0,S{D}_{\mathrm{age}}=1.0,55\text{\%}$ female). Results indicated no significant differences between the groups. Students interacted with the LLM in unexpected ways, demonstrating the need to supply resources and guidance. These results and the implications of LLM chatbots as an educational tool are discussed.