This paper explores the synergy between human cognition and Large Language Models (LLMs), highlighting how generative AI can drive personalized learning at scale. We discuss parallels between LLMs and human cognition, emphasizing both the promise and new perspectives on integrating AI systems into education. After examining challenges in aligning technology with pedagogy, we review AutoTutor-one of the earliest Intelligent Tutoring Systems (ITS)-and detail its successes, limitations, and unfulfilled aspirations. We then introduce the Socratic Playground, a next-generation ITS that uses advanced transformer-based models to overcome AutoTutor's constraints and provide personalized, adaptive tutoring. To illustrate its evolving capabilities, we present a JSON-based tutoring prompt that systematically guides learner reflection while tracking misconceptions. Throughout, we underscore the importance of placing pedagogy at the forefront, ensuring that technology's power is harnessed to enhance teaching and learning rather than overshadow it.

Many of the intelligent tutoring systems that have been developed during the last 20 years have proven to be quite successful, particularly in the domains of mathematics, science, and technology. They produce significant learning gains beyond classroom environments. They are capable of engaging most students' attention and interest for hours. We have been working on a new generation of intelligent tutoring systems that hold mixedinitiative conversational dialogues with the learner. The tutoring systems present challenging problems and questions to the learner, the learner types in answers in English, and there is a lengthy multiturn dialogue as complete solutions or answers evolve.

Struggling algebra students in the Everett, Wash., school district get help from special tutors who diagnose their weaknesses, tailor instruction to their needs, and provide on-the-spot feedback-all with an inhuman degree of patience. That's inhuman literally: The tutors are computers. Three years ago, the district started employing Cognitive Tutor, a series of computer programs based on artificial intelligence that were developed by researchers from Carnegie-Mellon University in Pittsburgh. The programs provide an alternative form of math instruction to secondary school students who haven't succeeded in regular classrooms. The experience proved so successful that officials in the 20,000-student district have expanded the program.

Emotion-sensing computer software that models and responds to students' cognitive and emotional states – including frustration and boredom – has been developed by University of Notre Dame Assistant Professor of Psychology Sidney D'Mello and colleagues from the University of Memphis and Massachusetts Institute of Technology. D'Mello also is a concurrent assistant professor of computer science and engineering. The new technology, which matches the interaction of human tutors, not only offers tremendous learning possibilities for students, but also redefines human-computer interaction. "AutoTutor" and "Affective AutoTutor" can gauge the student's level of knowledge by asking probing questions, analyzing the student's responses to those questions; proactively identifying and correcting misconceptions; responding to the student's own questions, gripes, and comments; and even sensing a student's frustration or boredom through facial expression and body posture and dynamically changing its strategies to help the student conquer those negative emotions. "Most of the 20th-century systems required humans to communicate with computers through windows, icons, menus, and pointing devices," says D'Mello, who specializes in human-computer interaction and artificial intelligence in education.

We evaluated an affect-sensitive version of AutoTutor, a dialogue based ITS that simulates human tutors. While the original AutoTutor is sensitive to students’ cognitive states, the affect-sensitive tutor (Supportive tutor) also responds to students’ affective states (boredom, confusion, and frustration) with empathetic, encouraging, and motivational dialogue moves that are accompanied by appropriate emotional expressions. We conducted an experiment that compared the Supportive and Regular (non-affective) tutors over two 30-minute learning sessions with respect to perceived effectiveness, fidelity of cognitive and emotional feedback, engagement, and enjoyment. The results indicated that, irrespective of tutor, students’ ratings of engagement, enjoyment, and perceived learning decreased across sessions, but these ratings were not correlated with actual learning gains. In contrast, students’ perceptions of how closely the computer tutors resembled human tutors increased across learning sessions, was related to the quality of tutor feedback, the increase was greater for the Supportive tutor, and was a powerful predictor of learning. Implications of our findings for the design of affect-sensitive ITSs are discussed.

This paper presents GnuTutor, an open source intelligent tutoring system (ITS) inspired by the AutoTutor ITS. The goal of GnuTutor is to create a freely available, open source ITS platform that can be used by schools and researchers alike. To achieve this goal, significant departures from AutoTutor's current design were made so that GnuTutor would use a smaller, non-proprietary code base but have the major functionality of AutoTutor, including mixed-initiative dialogue, an animated agent, speech act classification, and natural language understanding using latent semantic analysis. This paper describes the GnuTutor system, its components, and the major differences between GnuTutor and AutoTutor.

Vincent Aleven Intelligent tutoring systems (ITS) are highly effective in supporting student learning, but are difficult to build. The Cognitive Tutor Authoring Tools (CTAT) project started over 6 years ago with the goals of making it easier for experienced programmers, and possible for non-programmers to create an ITS. CTAT supports tutor building through programming by demonstration, an approach that has been successful in a range of application areas, but that has been applied to only a very limited degree to ITS authoring. Using CTAT, an author creates a tutor by demonstrating correct and incorrect problem solving behaviors, rather than by writing code. The resulting tutors, called exampletracing tutors, evaluate student behavior by flexibly comparing it against the demonstrated problem-solving examples.