Smart Homework Goals

Challenge

Personalized feedback helps students solve mathematics problems. Sustaining regular practice also requires clear goals, progress feedback, and support from teachers or tutors.

What We Do

Students choose weekly practice goals using recommendations based on their recent activity. The system tracks progress and supports goal review and adjustment. Teachers and tutors receive goal-achievement reports to guide follow-up, recognition, and rewards.

The work connects learning-platform data with classroom routines, supporting effort as well as problem solving.

Key Findings

An initial hybrid-tutoring study associated weekly goals and rewards with 25% more practice time and 40% more skills mastered.
In the adaptive-goal study, goal achievement after adjustment reached 36.4%, compared with 20.8% for static teacher-set goals in the same phase. The conditions differed in goal type and learner choice as well as adaptation.
The Fall 2025 interrupted time-series analysis included 522 students across four schools. Goal support was associated with 28% more weekly practice time and 52% more skills completed. The wider rollout covered 1,417 students across six schools. See Borchers (2026), Chapters 4–6, for more details.

Why it matters

The project studies how classroom goal routines and learning-platform data support regular mathematics practice. The results guide the design of recommendations, progress reports, and teacher-supported rewards.

The infrastructure has supported deployment across schools and platforms. Interpreting outcomes requires attention to the study design, implementation, and platform-specific measures.

Publications

Borchers, C., Nguyen, H. T., Carvalho, P. F., Koedinger, K. R., & Aleven, V. (2025). Goal Setting Engages More Caregivers Than Instructional Support in Online Math Homework. In Proceedings of the 20th European Conference on Technology Enhanced Learning (EC-TEL 2025). Newcastle and Durham, UK.

PDF: https://osf.io/preprints/edarxiv/5rej3_v1

Borchers, C., Houk, A., Aleven, V., & Koedinger, K. R. (2025). Engagement and Learning Benefits of Goal Setting with Rewards in Human-AI Tutoring. In Proceedings of the 26th International Conference on Artificial Intelligence in Education (AIED 2025). Palermo, Italy.

PDF: https://kilthub.cmu.edu/articles/journal_contribution/Engagement_and_Learning_Benefits_of_Goal_Setting_with_Rewards_in_Human-AI_Tutoring/29825675/1/files/56902463.pdf

Borchers, C., Koedinger, K. R., & Aleven, V. (2025). Intelligent Support for Practice Goal Setting to Enhance Learning. In International Conference on Artificial Intelligence in Education (pp. 397-402). Cham: Springer Nature Switzerland.

PDF: https://cborchers.com/pdf/2025-aied-Borchers-DC.pdf

Borchers, C., Peng, C., Lyu, Q., Carvalho, P. F., Koedinger, K. R., & Aleven, V. (2025). Student Perceptions of Adaptive Goal Setting Recommendations: A Design Prototyping Study. In Proceedings of the 26th International Conference on Artificial Intelligence in Education (AIED 2025). Palermo, Italy.

PDF: https://kilthub.cmu.edu/articles/conference_contribution/Student_Perceptions_of_Adaptive_Goal_Setting_Recommendations_A_Design_Prototyping_Study/29914484/1/files/57196406.pdf

Borchers, C. (2026). Personalized Goal Support to Enhance Technology-Supported Learning (Doctoral dissertation). Carnegie Mellon University.

PDF: https://cborchers.com/pdf/thesis.pdf

Grant Support

Digital Promise, Advancing Innovative Math Solutions (AIMS) Collaboratory, and Learning Data Insights. Large Grant: Improving Persistence through Adaptive Goal Setting in i-Ready ($250,000). PI: Conrad Borchers; Co-PIs: Vincent Aleven, Ken Koedinger, Danielle Thomas. 2026-2027.

Page updated

Report abuse