GPT-4 as a Homework Tutor can Improve Student Engagement and Learning Outcomes
Not on the map. Why?
Abstract (arXiv)
This work contributes to the scarce empirical literature on LLM-based interactive homework in real-world educational settings and offers a practical, scalable solution for improving homework in schools. Homework is an important part of education in schools across the world, but in order to maximize benefit, it needs to be accompanied with feedback and followup questions. We developed a prompting strategy that enables GPT-4 to conduct interactive homework sessions for high-school students learning English as a second language. Our strategy requires minimal efforts in content preparation, one of the key challenges of alternatives like home tutors or ITSs. We carried out a Randomized Controlled Trial (RCT) in four high-school classes, replacing traditional homework with GPT-4 homework sessions for the treatment group. We observed significant improvements in learning outcomes, specifically a greater gain in grammar, and student engagement. In addition, students reported high levels of satisfaction with the system and wanted to continue using it after the end of the RCT.
Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). First posted on arXiv 24 Sep 2024.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2025: 3; 2026: 6.
9 papers.
- 2025TutorBench: A Benchmark To Assess Tutoring Capabilities Of Large Language Modelscited by 11
- 2025A Meta-Analysis of LLM Effects on Students across Qualification, Socialisation, and Subjectificationcited by 2
- 2026Small, Private Language Models as Teammates for Educational Assessment Designcited by 2
- 2025Superstudent intelligence in thermodynamicscited by 1
- 2026Latency and Cost of Multi-Agent Intelligent Tutoring at Scalecited by 0
- 2026ITAS: A Multi-Agent Architecture for LLM-Based Intelligent Tutoringcited by 0
- 2026Sycophancy is an Educational Safety Risk: Why LLM Tutors Need Sycophancy Benchmarkscited by 0
- 2026Reflective Dialogue or Prompt Refinement? Effects of Tutor Scaffolding on Students' Independent LLM Use for Programmingcited by 0
- 2026ConnectED: A Curriculum-Aligned AI System for Vietnamese Instructional Lesson Planning and Student Learningcited by 0
- 2026Reflective Dialogue or Prompt Refinement? Effects of Tutor Scaffolding on Students' Independent LLM Use for Programming3 Jul 2026
- 2026ConnectED: A Curriculum-Aligned AI System for Vietnamese Instructional Lesson Planning and Student Learning2 Jun 2026
- 2026Small, Private Language Models as Teammates for Educational Assessment Design14 May 2026
- 2026Sycophancy is an Educational Safety Risk: Why LLM Tutors Need Sycophancy Benchmarks14 May 2026
- 2026ITAS: A Multi-Agent Architecture for LLM-Based Intelligent Tutoring27 Apr 2026
- 2026Latency and Cost of Multi-Agent Intelligent Tutoring at Scale27 Apr 2026
- 2025TutorBench: A Benchmark To Assess Tutoring Capabilities Of Large Language Models3 Oct 2025
- 2025A Meta-Analysis of LLM Effects on Students across Qualification, Socialisation, and Subjectification25 Sep 2025
- 2025Superstudent intelligence in thermodynamics11 Jun 2025