4 papers
TutorGym: A Testbed for Evaluating AI Agents as Tutors and Students
Daniel Weitekamp, Momin N. Siddiqui, Christopher J. MacLellan
Recent improvements in large language model (LLM) performance on academic benchmarks, such as MATH and GSM8K, have emboldened their use as standalone tutors and as simulations of h…
Beyond Final Answers: Evaluating Large Language Models for Math Tutoring
Adit Gupta, Jennifer Reddig, Tommaso Calo +2
Researchers have made notable progress in applying Large Language Models (LLMs) to solve math problems, as demonstrated through efforts like GSM8k, ProofNet, AlphaGeometry, and Mat…
Intelligent Tutors Beyond K-12: An Observational Study of Adult Learner Engagement and Academic Impact
Adit Gupta, Christopher MacLellan
Intelligent tutors have proven to be effective in K-12 education, though their impact on adult learners -- especially as a supplementary resource -- remains underexplored. Understa…
Intelligent Tutors for Adult Learners: An Analysis of Needs and Challenges
Adit Gupta, Momin Siddiqui, Glen Smith +2
This work examines the sociotechnical factors that influence the adoption and usage of intelligent tutoring systems in self-directed learning contexts, focusing specifically on adu…