KENNESAW, Ga. | Apr 1, 2026

If you were to sit in an online math class with them, Gabriel, Noah, and Jiwoo may sound like real elementary school students interacting in a virtual classroom, asking questions and making mistakes as they try to solve problems. In reality, they’re AI agents, better known as chatbots, helping to prepare future teachers to teach math more effectively.

The agents were developed by a Kennesaw State University researcher who is using artificial intelligence to help prepare future teachers for one of the most challenging aspects of the classroom: responding to how students think about math.

Funded by a three-year, $300,000 National Science Foundation grant, Associate Professor of Instructional Technology Dabae Lee developed an AI-powered agent system that simulates student interactions. The aim is to give pre-service teachers practice in “responsive teaching,” which is the ability to elicit and interpret students’ thinking and to extend their mathematical ideas by questioning.

“The major benefit is helping pre-service teachers develop their responsive teaching skills,” said Lee, who helps educate future teachers in the Clarice C. and Leland H. Bagwell College of Education. “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.”

Lee explained that the idea of the simulating agents came from Swiss psychologist Jean Piaget’s socio-cognitive conflict theory, which says students build a higher level of understanding by explaining and negotiating their perspectives with others who have different perspectives. For example, students who have different wrong answers to the same question can reach the correct answer by discussing their reasonings with one another. Responsive teaching allows teachers to elicit students’ own ways of thinking, sometimes with misconceptions, and to have productive conversations with them to help them resolve their misconceptions without taking over their thinking.

Student-teachers sometimes have limited opportunities to practice responding to students’ reasoning in real time, Lee noted. Traditional methods, such as peer role-playing, do not always reflect authentic classroom interactions.

“What has been done is that either the instructor, a trained adult or peer student-teachers will play the role of children,” Lee said. “It’s not ideal because adults may not respond the same as children would.”

The AI agents help to address that challenge by allowing student-teachers to interact with virtual students who respond uniquely to their explanations and questions in real-time.

Lee designed the system with three virtual students — Gabriel, Noah and Jiwoo – each with different personalities and varying mathematical skills.

“They are all different in terms of their personalities and their ways of thinking,” Lee said. “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.”

The system recently completed its second implementation in the fall with collaborators in the teacher education program at the University of Missouri and is currently being refined for another round of testing planned for next fall.

Lee said the feedback from student-teachers who have used the system has been favorable as many say the interactions feel more authentic than traditional practice exercises.

“The students really appreciated the ability of practicing responsive teaching with the virtual students,” Lee said.

Lee’s work has been published in the Computers & Education journal,  Journal of Computer Assisted Learning, and Journal of Mathematics Teacher Education.

The project, which initially used IBM Watsonx technology also captured the attention of IBM and was featured on IBM’s Smart Talks podcast, including a featured interview with renowned author and journalist Malcolm Gladwell.

Lee said the goal is to eventually share the technology more widely with teacher education programs.

“Our plan after the third round of testing is to make the agents and instructional modules accessible to other educators,” Lee said.

– Story by Christin Senior

Photos by Matt Yung

 

A leader in innovative teaching and learning, Kennesaw State University offers undergraduate, graduate, and doctoral degrees to its more than 51,000 students. Kennesaw State is a member of the University System of Georgia with 11 academic colleges. The university's vibrant campus culture, diverse population, strong global ties, and entrepreneurial spirit draw students from throughout the country and the world. Kennesaw State is a Carnegie-designated doctoral research institution (R2), placing it among an elite group of only 8 percent of U.S. colleges and universities with an R1 or R2 status. For more information, visit kennesaw.edu.