Abstract
Hybrid human-AI tutoring, where technology and humans jointly facilitate student learning, can be more beneficial than AI-only tutoring. However, preliminary evidence sug gests that lower-performing students derive greater benefit from human-AI tutoring than higher-performing students. As such, this study evaluates whether a differentiated tu toring policy can effectively support both groups: human tutors initiate support for lower-performing students, while higher-performing students receive reactive, on-demand sup port. Using their within-grade median state test scores, we assigned 635 students (grades 5 − 8) to receive proac tive (< median) or reactive (≥ median) tutoring. Us ing a difference-in-discontinuities (DiDC) design, we com pare outcomes across two time periods: fall (AI-only tu toring for all) and spring (proactive-reactive human-AI tu toring). This quasi-experimental design isolates the effects of proactive-reactive tutoring approaches by comparing the discontinuity in spring outcomes to the fall baseline, where no such discontinuity existed. Using data around the cutoff (Imbens-Kalyanaraman criterion), we find significant overall improvements from human-AI tutoring compared to AI-only baseline: 25% increase in time on task, 36% in skill pro ficiency, and 61% in academic growth (standardized MAP test). Between proactive and reactive tutoring, we find com parable improvements in time-on-task and skill proficiency (i.e., no significant difference). We also did not find a signif icant difference in MAP growth at the cutoff itself, however, proactive tutoring, on average, showed marginally higher MAP growth (75%, p = .065) than reactive tutoring, i.e., proactive tutoring was more beneficial to students farther below the cutoff and helped narrow achievement gaps. Our findings provide evidence that differentiated human-AI tu toring addresses the needs of both groups, offering a practi cal and cost-effective strategy for scaling hybrid instruction. Keywords Human-AI Tutoring, Academic Growth, Remote Tutoring, Difference-in-Discontinuities
Showing the abstract — retrieve the full paper via the Exa API.