Improving Hybrid Human-AI Tutoring by Differentiating Human Tutor Roles Based on Student Needs
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909034158751744 |
|---|---|
| author | Gurung, Ashish Gao, Ge Gutterman, Jordan Thomas, Danielle R. Gupta, Shivang Branstetter, Lee Brunskill, Emma Aleven, Vincent Koedinger, Kenneth R. |
| author_facet | Gurung, Ashish Gao, Ge Gutterman, Jordan Thomas, Danielle R. Gupta, Shivang Branstetter, Lee Brunskill, Emma Aleven, Vincent Koedinger, Kenneth R. |
| contents | Hybrid human-AI tutoring, where technology and humans jointly facilitate student learning, can be more beneficial than AI-only tutoring. However, preliminary evidence suggests that lower-performing students derive greater benefit from human-AI tutoring than higher-performing students. As such, this study evaluates whether a differentiated tutoring policy can effectively support both groups: human tutors initiate support for lower-performing students, while higher-performing students receive reactive, on-demand support. Using their within-grade median state test scores, we assigned 635 students (grades 5-8) to receive proactive (< median) or reactive ($\geq$ median) tutoring. Using a DiDC design, we compare outcomes across two time periods: fall (AI-only tutoring) and spring (proactive-reactive human-AI tutoring). This quasi-experimental design isolates the effects of proactive-reactive tutoring approaches by comparing the discontinuity in spring outcomes to the fall, 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 proficiency, and 61% in academic growth (standardized MAP test). Between proactive and reactive tutoring, we find comparable improvements in time-on-task and skill proficiency. 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 tutoring addresses the needs of both groups, offering a practical and cost-effective strategy for scaling hybrid instruction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_11155 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Improving Hybrid Human-AI Tutoring by Differentiating Human Tutor Roles Based on Student Needs Gurung, Ashish Gao, Ge Gutterman, Jordan Thomas, Danielle R. Gupta, Shivang Branstetter, Lee Brunskill, Emma Aleven, Vincent Koedinger, Kenneth R. Computers and Society Hybrid human-AI tutoring, where technology and humans jointly facilitate student learning, can be more beneficial than AI-only tutoring. However, preliminary evidence suggests that lower-performing students derive greater benefit from human-AI tutoring than higher-performing students. As such, this study evaluates whether a differentiated tutoring policy can effectively support both groups: human tutors initiate support for lower-performing students, while higher-performing students receive reactive, on-demand support. Using their within-grade median state test scores, we assigned 635 students (grades 5-8) to receive proactive (< median) or reactive ($\geq$ median) tutoring. Using a DiDC design, we compare outcomes across two time periods: fall (AI-only tutoring) and spring (proactive-reactive human-AI tutoring). This quasi-experimental design isolates the effects of proactive-reactive tutoring approaches by comparing the discontinuity in spring outcomes to the fall, 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 proficiency, and 61% in academic growth (standardized MAP test). Between proactive and reactive tutoring, we find comparable improvements in time-on-task and skill proficiency. 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 tutoring addresses the needs of both groups, offering a practical and cost-effective strategy for scaling hybrid instruction. |
| title | Improving Hybrid Human-AI Tutoring by Differentiating Human Tutor Roles Based on Student Needs |
| topic | Computers and Society |
| url | https://arxiv.org/abs/2605.11155 |