← All research

AI for Learning

Students learn math better with AI when their interactions evolve over time towards more active and strategic engagement with concepts, rather than just seeking answers.

cs.CYBeginner-friendly

From Prompting to Epistemic Proactivity: Temporal Trajectories of Student-AI Interaction in Mathematics Learning

Rania Abdelghani, Peter Kaiser, Kou Murayama

In plain terms

This study explored how Grade-9 students interact with general-purpose AI tools, like ChatGPT, for learning mathematics in open-ended settings, aiming to understand what kind of interaction leads to better understanding. The researchers observed 112 students using an AI tutor for math practice, analyzing their conversations with the AI. They coded student messages for self-regulated learning behaviors, types of help requested, and engagement in mathematical problem-solving, specifically looking at how these patterns changed over time during a session. They found that simply summarizing a student's overall AI use, like the total number of questions, did not predict learning outcomes. However, students performed better when their interactions showed a temporal shift: moving towards more conceptual or procedural help-seeking and independent mathematical work in later stages, instead of primarily asking for answers or verification. This suggests that actively and strategically guiding the AI to advance one's understanding, termed "epistemic proactivity," is key for productive learning.

Why it matters · This paper is important for newcomers because it demonstrates that the *quality and evolution* of student-AI interaction, not just basic engagement, are critical for effective learning. It encourages researchers and designers to think beyond static usage metrics and focus on building AI systems that foster dynamic, self-regulated learning trajectories.

About this work · This research is situated in the field of AI in education, investigating the practical application of large language models (LLMs) as learning companions. It specifically examines how students interact with these tools in mathematics learning and how these interactions relate to improved academic performance.

LLMs in educationstudent-AI interactionmathematics educationself-regulated learninglearning analytics