Reproduce “Evaluating the Design Features of an Intelligent Tutoring System for Advanced Mathematics Learning” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Ying Fang, Bo He, Zhi Liu, Sannyuya Liu, Zhonghua Yan, Jianwen Sun
Xiaomai supports Chinese college students preparing for an advanced-mathematics graduate-school entrance exam. Students upload handwritten solutions, compare them with worked answers, and assess their own work; after errors, they can identify a cause. In a 40-minute trial, multiple-choice groups attempted 21.98 questions on average, versus 15.41 for free-response groups. Adjusted posttest results favored multiple-choice practice only marginally (p = .06), so the trial established no learning advantage for free-response practice.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.