Kennesaw State University Associate Professor of Instructional Technology Dabae Lee announced on Apr. 1 that she has developed an artificial intelligence-powered agent system to help prepare future teachers for teaching mathematics. The project is supported by a three-year, $300,000 grant from the National Science Foundation.
The initiative aims to improve “responsive teaching” skills among pre-service teachers by simulating real-time interactions with virtual students. Responsive teaching involves eliciting and interpreting students’ thinking and extending their mathematical ideas through questioning.
Lee said, “The major benefit is helping pre-service teachers develop their responsive teaching skills. In turn, that will help their future students develop mathematical reasoning and positive attitudes toward mathematics, which has been an area that students in the U.S. have always struggled with.”
The AI system features three virtual student agents—Gabriel, Noah, and Jiwoo—each designed with distinct personalities and mathematical abilities. According to Lee, “They are all different in terms of their personalities and their ways of thinking… Gabrielle is a playful student who is strong in math, while Noah shares the same playful personality but struggles with the subject. Jiwoo is articulate but has specific misconceptions about certain math concepts.”
Lee explained that traditional methods like peer role-playing do not always provide authentic classroom experiences because adults may not respond as children would. She said, “What has been done is that either the instructor, a trained adult or peer student-teachers will play the role of children… It’s not ideal because adults may not respond the same as children would.” The new AI agents address this challenge by offering unique responses during practice sessions.
Feedback from student-teachers who have used the system has been positive. “The students really appreciated the ability of practicing responsive teaching with the virtual students,” Lee said.
After its second round of implementation at Kennesaw State University and in collaboration with teacher education programs at other institutions such as University of Missouri, further testing is planned for next fall. The project was initially built using IBM Watsonx technology and was featured on IBM’s Smart Talks podcast.
Looking ahead, Lee stated: “Our plan after the third round of testing is to make the agents and instructional modules accessible to other educators.”
