TutorGym connects LLMs, RL agents, and computational learning models to 223 existing tutoring domains, and initial evaluations show LLMs grade steps poorly but can imitate human learning curves with in-context learning.
Artificial intelligence42(1), 7–49 (1990)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TutorGym: A Testbed for Evaluating AI Agents as Tutors and Students
TutorGym connects LLMs, RL agents, and computational learning models to 223 existing tutoring domains, and initial evaluations show LLMs grade steps poorly but can imitate human learning curves with in-context learning.