Reproduce “Improving Student Learning with Hybrid Human-AI Tutoring: A Three-Study Quasi-Experimental Investigation” 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
Danielle R. Thomas, Jionghao Lin, Erin Gatz, Ashish Gurung, Shivang Gupta, Kole Norberg, Stephen E. Fancsali, Vincent Aleven and 3 more
This research from Carnegie Mellon University and collaborators investigated a hybrid human-AI tutoring model for middle school math, finding it increased student engagement and learning outcomes, particularly for those with lower baseline abilities. The approach integrates AI for adaptive instruction with human tutors for socio-motivational support, presenting a scalable and cost-effective alternative to traditional tutoring.
Key insights
- Hybrid human-AI tutoring significantly enhances student engagement with math software and improves intermediate learning outcomes compared to using software alone.
- The benefits of hybrid tutoring are more pronounced for students with lower baseline abilities or those significantly below grade level, indicating its potential for narrowing achievement gaps.
- Providing human tutors with real-time dashboards to monitor student progress allows for more efficient and targeted support, increasing student productivity within the learning software.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.