In this paper, we describe an innovative infrastructure to support student participation and collaboration and help the instructor manage large or distance classrooms using multiagent system intelligence. The system, called I-MINDS, has a host of intelligent agents for each classroom: a teacher agent ranks and categorizes real-time questions from the students and collects statistics on student participation, a number of group agents that each maintains a collaborative group and facilitate student discussions, and a student agent for each student that profiles a student and finds compatible students to form the student's "buddy group". Each agent is capable of machine learning, thus improving its performance and services over time. These agents also interact and collaborate among themselves to exchange information and form coalitions dynamically to better serve the users. We have pilot-tested I-MINDS in GIS lectures, deployed I-MINDS in an introductory computer science course (CS1) 's laboratory, and evaluated the impact of I-MINDS based on student assessment. The results showed that students using I-MINDS performed (and outperformed in some aspects) as well as students in traditional settings.