ABSTRACT
The Tutoring Research Group at the University of Memphis has developed a series of tutoring systems with animated conversational agents. One of these systems is AutoTutor. AutoTutor has been developed for three subject matters so far: Newtonian qualitative physics, introductory computer literacy, and military tactical reasoning. The design of AutoTutor was inspired by explanation-based constructivist theories of learning, intelligent tutoring systems that adaptively respond to student knowledge, and empirical research on dialog patterns in tutorial discourse. AutoTutor presents challenging problems from a curriculum script and then engages in mixed initiative dialog that guides the student in building an answer. AutoTutor provides feedback to the student on what the student types in, pumps the student for more information, prompts the student to fill in missing words, gives hints, fills in missing information with assertions, identifies and corrects erroneous ideas and misconceptions, answers the student's questions, and summarizes answers.
