The DOI matches its Crossref record; 69 of the 69 references it cites were found in a registry or an index.
Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise
Open accessAbstract
Generative AI, particularly Language Models (LMs), has the potential to transform real-world domains with societal impact, particularly where access to experts is limited. For example, in education, training novice educators with expert guidance is important for effectiveness but expensive, creating significant barriers to improving education quality at scale. This challenge disproportionately hurts students from under-served communities, who stand to gain the most from high-quality education and are most likely to be taught by inexperienced educators. We introduce Tutor CoPilot, a novel Human-AI approach that leverages a model of expert thinking to provide expert-like guidance to tutors as they tutor. This study presents the first randomized controlled trial of a Human-AI system in live tutoring, involving 900 tutors and 1,800 K-12 students from historically under-served communities. Following a preregistered analysis plan, we find that students working on mathematics with tutors randomly assigned to have access to Tutor CoPilot are 4 percentage points (p.p.) more likely to master topics (p<0.01). Notably, students of lower-rated tutors experienced the greatest benefit, improving mastery by 9 p.p. relative to the control group. We find that Tutor CoPilot costs only $20 per-tutor annually, based on the tutors’ usage during the study. We analyze 550,000+ messages using classifiers to identify pedagogical strategies, and find that tutors with access to Tutor CoPilot are more likely to use strategies that foster student understanding (e.g., asking guiding questions) and less likely to give away the answer to the student, aligning with high-quality teaching practices. Tutor interviews qualitatively highlight how Tutor CoPilot’s guidance helps them to respond to student needs, though tutors flag common issues in Tutor CoPilot, such as generating suggestions that are not grade-level appropriate. Altogether, our study of Tutor CoPilot demonstrates how Human-AI systems can scale expertise in real-world domains in real time, bridge gaps in skills and create a future where high-quality education is accessible to all students. 1
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Those Who Understand: Knowledge Growth in Teaching
SHULMAN, L. S. (1986) · Educational Researcher · doi:10.3102/0013189x015002004 · Cited by 18,546
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515
School readiness and later achievement.
Duncan, G. J., Dowsett, C. J., Claessens, A., Magnuson, K., Huston, A. C., Klebanov, P., Pagani, L. S., Feinstein, L., Engel, M., Brooks-Gunn, J., et al. (2007) · Developmental Psychology · doi:10.1037/0012-1649.43.6.1428 · Cited by 5,439
Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025
Visible learning: a synthesis of over 800 meta‐analyses relating to achievement
Carter, M. (2009) · Educational Psychology · doi:10.1080/01443410903415150 · Cited by 4,581
Effective Teacher Professional Development
Darling-Hammond, L., Hyler, M., & Gardner, M. (2017) · Learning Policy Institute · doi:10.54300/122.311 · Cited by 4,264
Class-Balanced Loss Based on Effective Number of Samples
Cui, Y., Jia, M., Lin, T.-Y., Song, Y., & Belongie, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00949 · Cited by 3,094
Effects of Teachers’ Mathematical Knowledge for Teaching on Student Achievement
Hill, H. C., Rowan, B., & Ball, D. L. (2005) · American Educational Research Journal · doi:10.3102/00028312042002371 · Cited by 2,812
The Work of Teaching and the Challenge for Teacher Education
Loewenberg Ball, D., & Forzani, F. M. (2009) · Journal of Teacher Education · doi:10.1177/0022487109348479 · Cited by 1,675
Teacher Sorting and the Plight of Urban Schools: A Descriptive Analysis
Lankford, H., Loeb, S., & Wyckoff, J. (2002) · Educational Evaluation and Policy Analysis · doi:10.3102/01623737024001037 · Cited by 1,454
Self-citation
Cited by
Generative AI without guardrails can harm learning: Evidence from high school mathematics
Bastani, H., Bastani, O., Sungu, A., Ge, H., Kabakcı, Ö., & Mariman, R. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2422633122 · Cited by 309
The implications of generative artificial intelligence for mathematics education
Walkington, C. (2025) · School Science and Mathematics · doi:10.1111/ssm.18356 · Cited by 80
Hicke, Y., Geathers, J., Vu, K. V., Sewell, J. L., Cardie, C., Talwalkar, J. S., Shung, D. L., Jack, A. G., Cornes, S. B., Preston, M., et al. (2026) · International Conference on Learning Analytics and Knowledge (LAK) · doi:10.1145/3785022.3785092 · Cited by 63
Training LLM-Based Tutors to Improve Student Learning Outcomes in Dialogues
Scarlatos, A., Liu, N.-S., Lee, J., Baraniuk, R. G., & Lan, A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-98414-3_18 · Cited by 56
Math Education with Large Language Models: Peril or Promise?
Kumar, H., Rothschild, D. M., Goldstein, D. G., & Hofman, J. (2023) · doi:10.2139/ssrn.4641653 · Cited by 54
Metadata
- Authors
- Wang, R., Ribeiro, A., Robinson, C., Loeb, S., & Demszky, D.
- Affiliations
- Stanford University (US)
- Stanford University
- Corresponding author
- Wang, Rose
- Venue
- Research Square
- Published
- 2024-11-25
- OpenAlex
- W4404666730
- Cited by
- 53
- References
- 63
- Citations by year
- 2026: 30 · 2025: 23
- Type
- posted content
- Language
- en
- Open access
- green
- doi.org
- Locations
- Research Square (acceptedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
- Social Sciences › Education › Artificial Intelligence in Education
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- K-12 mathematics education, teaching methods, guiding questions
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise. https://app.cochat.ai/papers/10.21203/rs.3.rs-5363154/v1
- The paper
- Wang, R., Ribeiro, A., Robinson, C., Loeb, S., & Demszky, D. (2024). Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise. Research Square. https://doi.org/10.21203/rs.3.rs-5363154/v1
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.