# How Real Is AI Tutoring? Comparing Simulated and Human Dialogues in One-on-One Instruction

arXiv: https://arxiv.org/abs/2509.01914 · HTML: https://mlsanity.com/paper/2509.01914/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 46 references that are in the map.
- First posted on arXiv 2 Sep 2025.

## Builds on (most cited first, 7 of 7)

- [Generative AI](https://mlsanity.com/paper/2309.07930/) (2023)
- [Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challenges](https://mlsanity.com/paper/2409.02387/) (2024)
- [CGMI: Configurable General Multi-Agent Interaction Framework](https://mlsanity.com/paper/2308.12503/) (2023)
- [Learning-by-teaching with ChatGPT: The effect of teachable ChatGPT agent on programming education](https://mlsanity.com/paper/2412.15226/) (2024)
- [High-Ratio Compression for Machine-Generated Data](https://mlsanity.com/paper/2311.13947/) (2023)
- [MAS-KCL: Knowledge component graph structure learning with large language model-based agentic workflow](https://mlsanity.com/paper/2505.14126/) (2025)
- [IntelliChain: An Integrated Framework for Enhanced Socratic Method Dialogue with LLMs and Knowledge Graphs](https://mlsanity.com/paper/2502.00010/) (2025)

## Built on by (most cited first, 2 of 2)

- [The Missing Evaluation Axis: What 10,000 Student Submissions Reveal About AI Tutor Effectiveness](https://mlsanity.com/paper/2605.05648/) (2026)
- [Thinking in Graphs with CoMAP: A Shared Visual Workspace for Designing Project-Based Learning](https://mlsanity.com/paper/2604.06200/) (2026)

## Abstract (arXiv)

Heuristic and scaffolded teacher-student dialogues are widely regarded as critical for fostering students' higher-order thinking and deep learning. However, large language models (LLMs) currently face challenges in generating pedagogically rich interactions. This study systematically investigates the structural and behavioral differences between AI-simulated and authentic human tutoring dialogues. We conducted a quantitative comparison using an Initiation-Response-Feedback (IRF) coding scheme and Epistemic Network Analysis (ENA). The results show that human dialogues are significantly superior to their AI counterparts in utterance length, as well as in questioning (I-Q) and general feedback (F-F) behaviors. More importantly, ENA results reveal a fundamental divergence in interactional patterns: human dialogues are more cognitively guided and diverse, centered around a "question-factual response-feedback" teaching loop that clearly reflects pedagogical guidance and student-driven thinking; in contrast, simulated dialogues exhibit a pattern of structural simplification and behavioral convergence, revolving around an "explanation-simplistic response" loop that is essentially a simple information transfer between the teacher and student. These findings illuminate key limitations in current AI-generated tutoring and provide empirical guidance for designing and evaluating more pedagogically effective generative educational dialogue systems.