Lan Luo, Anqi Wang, Muzhi Zhou, Junhua Zhu, Jie Cai, Ao Yu, Hui Pan (2026). arXiv cs.HC 📄 Full text (arXiv)
Key Findings
Generic LLM assistance reduces the parent's tutoring role; ParaTutor preserves parent-led support and sustains child reasoning through role-separated scaffolding. LLM support for multi-user learning must be distributed by user roles.
Relevance to AI in Education
This paper contributes directly to understanding how AI systems interact with learners in authentic educational settings. Shows that role-separated LLM scaffolding preserves parent-led tutoring dynamics, unlike generic LLM assistance that reduces the parent role.
Related Pages
- scaffolding — related page
- intelligent-tutoring-systems — related page
- k-12 — related page
- ai-learning-companions-framework — related page
- conversational-ai-tutors-framework — related page
Citation
APA: Lan Luo, Anqi Wang, Muzhi Zhou, Junhua Zhu, Jie Cai, Ao Yu, Hui Pan (2026). ParaTutor: LLM Mediated Parent Child Tutoring through Role Separated Scaffolding Interface in Real Time. arXiv:2606.18030. arXiv cs.HC.