In this paper, we describe a computer-supported cooperative learning system in education and the results of its deployment. The system, called I-MINDS, consists of a set of teacher agents, group agents, and student agents. While the agents possess individual intelligent capabilities, the novel invention of I-MINDS lies in multiagent intelligence and coalition formation. I-MINDS supports student participation and collaboration and helps the instructor manage large, distance classrooms. Specifically, it uses a Vickrey auction-based and learning-enabled algorithm called VALCAM to form student groups in a structured cooperative learning setting. We have deployed I-MINDS in an introductory computer science course (CS1) and conducted experiments in the Spring and Fall semesters of 2005 to study how I-MINDS-supported collaboration fares against traditional, face-to-face collaboration. Results showed that students using I-MINDS performed (and outperformed in some aspects) as well as students in traditional settings.