Cognitive Tutors


Contributor: Daniel Sommerhoff (Ludwig-Maximilians-Universität München)

Generally, intelligent tutoring systems (ITS) can be defined as computer-based learning environments aimed at supporting students in mastering specific skills or knowledge (see Graesser, Hu, Sottilare, 2018). In comparison to typical learning environments, which include texts, exercises, and human conversations, ITS are based on the computer-based implementation of results from cognitive science on human learning (e.g., ACT-R) and domain-specific educational research on the specific learning content of the ITS. Multiple ITS have been developed so far, especially in the area of well-defined problems in mathematics, where cognitive tutors have a long tradition, but also in other areas such as physics or information technology (see Anderson et al., 1995).

ITS and cognitive tutors are often described as practical applications of cognitive science combined with artificial intelligence technology. Additionally, it is noteworthy that most ITS are examples for design-based research of learning theory application. When studied empirically, the application of learning theories in ITS can be used to create new knowledge that can be used to advance the learning theory itself. In short, with ITS, the learning sciences and learning environment applications of learning sciences are reciprocally advancing one another when ITS learning environment designs are created and studied in their uses for advancing human learning.

ITS aim to provide an individualized and (based on the given information) optimized learning experience that provides a human-like tutoring experience. Traditionally, ITS emerged from the boundary between cognitive psychology and computer sciences (see Polson & Richardson, 2013). However, as today multiple authoring tools for ITS exist that only require minimal programming skills, ITS have also attracted researchers and research groups with little background in computer sciences, programming, and artificial intelligence.

ITS are based on multiple key design features, including: i) nested loops of learners’ reading, working on exercises, and being tested, ii) step-by-step learner feedback while working on exercises, iii) knowledge tracing, and iv) individual task selection. When working with a cognitive tutor, the learner’s knowledge, skills, and possibly also other attributes are tracked to adaptively respond to the user’s learning by using computational models based on artificial intelligence and models from cognitive science. With such design architecture features, a user’s possible interaction sequences with a cognitive tutor are computationally vast, enabling highly customized learning experiences for every learner rather than the common aggregate instruction of face-to-face classroom teaching.

Over several decades, ITS have repeatedly proven successful, in promoting demonstrable learning outcomes at scale as multiple commercial tools have emerged from foundational ITS research. Especially within the domain of mathematics, ITS have shown positive and long-term effects in multiple content areas, such as geometry, algebra, or arithmetic. Multiple large field studies have underlined their effectiveness also outside laboratory settings. Moreover, meta-analytic findings underline: i) their effectiveness compared to teacher-led large group instruction, non-ITS computer-based instruction, and text-/workbooks and ii) only non-significant differences of ITS compared to learning with human tutors or small-group instruction.

Syllabi and Slides

Cognitive Tutors slides by Vincent Aleven

Video Resources

Listen to the Cognitive Tutors webinar


Basic Reading:
  • Anderson, J. R., Corbett, A. T., Koedinger, K. R. & Pelletier, R. (1995). Cognitive Tutors: Lessons Learned. The Journal of the Learning Sciences, 4(2), 167-207. [Access Online]
  • Graesser, A. C., Hu, X., & Sottilare, R. (2018). Intelligent tutoring systems. International handbook of the learning sciences, 246-255.
  • Koedinger, K. R., & Corbett, A. T. (2006). Cognitive Tutors: Technology bringing learning science to the classroom. In R. K. Sawyer (Ed.), The Cambridge Handbook of the Learning Sciences, (pp. 61-78). Cambridge University Press. [Access Online]
  • Polson, M. C., & Richardson, J. J. (2013). Foundations of intelligent tutoring systems. Psychology Press.
Additional Reading:
  • Aleven, V. A., & Koedinger, K. R. (2002). An effective metacognitive strategy: Learning by doing and explaining with a computer-based cognitive tutor. Cognitive Science, 26(2), 147-179.
  • Aleven, V., McLaren, B. M., Sewall, J., & Koedinger, K. (2009). A new paradigm for intelligent tutoring systems: Example-tracing tutors. International Journal of Artificial Intelligence in Education, 19, 105-154.
  • Aleven, V., Roll, I., & Koedinger, K. R. (2012). Progress in assessment and tutoring of lifelong learning skills: An intelligent tutor agent that helps students become better help seekers. In P. J. Durlach & A. M. Lesgold (Eds.), Adaptive technologies for training and education (pp. 69-95). New York: Cambridge University Press.
  • Anderson, J. R., Conrad, F. G., & Corbett, A. T. (1989). Skill acquisition and the LISP tutor. Cognitive Science, 13(4), 467-505. [doi: 10.1016/0364- 0213(89)90021-9]
  • Corbett, A., McLaughlin, M., & Scarpinatto, K. C. (2000). Modeling student knowledge: Cognitive tutors in high school and college. User Modeling and UserAdapted Interaction, 10, 81-108.
  • Graesser, A.C., Hu, X., Nye, B., Sottilare, R. (2016). Intelligent tutoring systems, serious games, and the Generalized Intelligent Framework for Tutoring (GIFT). In H.F. O’Neil, E.L. Baker, and R.S. Perez. (Eds.), Using games and simulation for teaching and assessment (pp. 58-79). Routledge: Abingdon, Oxon, UK.
  • Kalena Cortes, Takako Nomi and Joshua Goodman. A double dose of Algebra: Intensive math instruction has long-term benefits. EducationNext, Winter 2013/Vol. 13, No. 1. [Access Online]
  • Koedinger, K. R., & Aleven, V. (2007). Exploring the assistance dilemma in experiments with cognitive tutors. Educational Psychology Review, 19(3), 239-264.
  • Koedinger, K. R., & Corbett, A. T. (2006). Cognitive Tutors: Technology bringing learning science to the classroom. In R. K. Sawyer (Ed.), The Cambridge Handbook of the Learning Sciences, (pp. 61-78). Cambridge University Press.
  • Ma, W., Adesope, O. O., Nesbit, J. C., & Liu, Q. (2014). Intelligent tutoring systems and learning outcomes: A meta-analytic survey. Journal of Educational Psychology, 106, 901-918.
  • Olsen, J.K., Rummel, N. & Aleven, V. It is not either or: An initial investigation into combining collaborative and individual learning using an ITS. International Journal of Computer-Supported Collaboration, Learn 14, 353-381 (2019).
  • Pane, J. F., Griffin, B. A., McCaffrey, D. F., & Karam, R. (2013). Effectiveness of Cognitive Tutor Algebra I at Scale. Educational Evaluation and Policy Analysis, 0162373713507480. [doi: 10.3102/0162373713507480]
  • Ritter, S., Anderson, J. R., Koedinger, K. R., Corbett, A. (2007) Cognitive Tutor: Applied Research in Mathematics Education. Psychonomic Bulletin & Review, 14, 249-255.
Additional Resources:

Learning Scientists Who Have Researched This Topic

  • John Anderson
  • Vincent Aleven
  • Albert Corbett
  • Arthur C. Graesser
  • Xiangen Hu
  • Kenneth Koedinger
  • Kurt van Lehn
  • Jennifer Olsen
  • Brian Reiser
  • Steve Ritter
  • Nikol Rummel
  • Robert Sottilare