Improving Hybrid Human-AI Tutoring by Differentiating the Human Tutor’s Role Based on Student Need

Hybrid human-AI tutoring research highlights the promise of scaling personalized learning by combining adaptive AI tutor support with personalized instructional and motivational guidance from human tutors. However, emerging evidence suggests that human-AI tutoring is more beneficial for lower-performing students than higher-performing peers. This study evaluates a proactive-reactive personalization policy, where human tutors proactively initiate support for lower-performing students (below median), while higher-performing students receive reactive, on-demand support. Using a quasi-experimental difference-in-discontinuities design, 635 students (grades 5–8) were assigned to receive proactive or reactive tutoring during math practice using IXL (an AI tutor). Treatment assignment was determined using within-grade median state test scores.

Results indicate that human-AI tutoring led to 43% (p = .01) growth on standardized tests compared to AI-only tutoring (i.e., 2.0× vs. 1.4× of expected growth). While the effects benefited both human-AI tutoring, the performance improvement was marginally greater than reactive tutoring (0.13 SD, p = .059). Beyond standardized tests, human-AI tutoring significantly increased students’ time-on-task (+1.38 hours, p < .001) and skill proficiency (+6.87 skills, p < .001) compared to AI-only tutoring. Finally, mediation analysis reveals a direct benefit of proactive tutoring on standardized test performance, despite lower time on task and skill proficiency compared to reactive tutoring—suggesting a “slow to go fast” dynamic where learning from direct interactions with tutors went beyond learning from IXL alone.

Overall, the findings provide empirical evidence that access to human-AI tutoring leads to greater academic growth compared to AI-only tutoring, particularly for lower-performing students. More practically, these findings highlight a cost-effective strategy for scaling human-AI tutoring by allocating resources based on student needs, while improving learning for all students.