Can we devise educational systems that provide individualized instruction tailored to the needs of the individual learners, as many good teachers do? Intelligent Tutoring Systems is the interdisciplinary field that investigates this question by integrating research in Artificial Intelligence, Cognitive Science and Education. Successful intelligent tutoring systems have been deployed to support traditional problem solving activities by tailoring the instruction to the student's domain knowledge. In this talk, I will present a variety of projects that illustrate our efforts to extend the scope of intelligent tutors to both support novel forms of pedagogical interactions (e.g., example-based and exploration-based learning) and adapt to student's traits beyond knowledge (e.g., student's meta-cognitive abilities and affective states). I will discuss the challenges of this research, the results that we have achieved so far and future opportunities.