# Which Type of Students can LLMs Act? Investigating Authentic Simulation with Graph-based Human-AI Collaborative System

arXiv: https://arxiv.org/abs/2502.11678 · HTML: https://mlsanity.com/paper/2502.11678/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 32 references that are in the map.
- First posted on arXiv 17 Feb 2025.

## Builds on (most cited first, 16 of 16)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Large Language Models for Education: A Survey and Outlook](https://mlsanity.com/paper/2403.18105/) (2024)
- [Design Space for Graph Neural Networks](https://mlsanity.com/paper/2011.08843/) (2020)
- [Simulating Classroom Education with LLM-Empowered Agents](https://mlsanity.com/paper/2406.19226/) (2024)
- [Generative Students: Using LLM-Simulated Student Profiles to Support Question Item Evaluation](https://mlsanity.com/paper/2405.11591/) (2024)
- [Exploring Knowledge Tracing in Tutor-Student Dialogues using LLMs](https://mlsanity.com/paper/2409.16490/) (2024)
- [TeachTune: Reviewing Pedagogical Agents Against Diverse Student Profiles with Simulated Students](https://mlsanity.com/paper/2410.04078/) (2024)
- [The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models](https://mlsanity.com/paper/2305.14999/) (2023)
- [Language Model Can Do Knowledge Tracing: Simple but Effective Method to Integrate Language Model and Knowledge Tracing Task](https://mlsanity.com/paper/2406.02893/) (2024)
- [From MOOC to MAIC: Reshaping Online Teaching and Learning through LLM-driven Agents](https://mlsanity.com/paper/2409.03512/) (2024)
- [Personality-aware Student Simulation for Conversational Intelligent Tutoring Systems](https://mlsanity.com/paper/2404.06762/) (2024)
- [Explainable Few-shot Knowledge Tracing](https://mlsanity.com/paper/2405.14391/) (2024)
- [A Review of Data Mining in Personalized Education: Current Trends and Future Prospects](https://mlsanity.com/paper/2402.17236/) (2024)

## Built on by (most cited first, 9 of 9)

- [Simulated Students in Tutoring Dialogues: Substance or Illusion?](https://mlsanity.com/paper/2601.04025/) (2026)
- [TeachLM: Post-Training LLMs for Education Using Authentic Learning Data](https://mlsanity.com/paper/2510.05087/) (2025)
- [FACET: Teacher-Centred LLM-Based Multi-Agent Systems-Towards Personalized Educational Worksheets](https://mlsanity.com/paper/2508.11401/) (2025)
- [Who Am I? History-Aware Profiles for Student Simulation in Tutoring Dialogues](https://mlsanity.com/paper/2605.30051/) (2026)
- [ParaStudent: Closing the Sim2Real Gap in User Simulators for AI Tutor Evaluation](https://mlsanity.com/paper/2507.12674/) (2025)
- [Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues](https://mlsanity.com/paper/2605.01097/) (2026)
- [SmartCourse: A Contextual AI-Powered Course Advising System for Undergraduates](https://mlsanity.com/paper/2507.22946/) (2025)
- [Metacognition in LLMs: Foundations, Progress, and Opportunities](https://mlsanity.com/paper/2607.11881/) (2026)
- [Student Development Agent: Risk-free Simulation for Evaluating AIED Innovations](https://mlsanity.com/paper/2510.09183/) (2025)

## Abstract (arXiv)

While rapid advances in large language models (LLMs) are reshaping data-driven intelligent education, accurately simulating students remains an important but challenging bottleneck for scalable educational data collection, evaluation, and intervention design. However, current works are limited by scarce real interaction data, costly expert evaluation for realism, and a lack of large-scale, systematic analyses of LLMs ability in simulating students. We address this gap by presenting a three-stage LLM-human collaborative pipeline to automatically generate and filter high-quality student agents. We leverage a two-round automated scoring validated by human experts and deploy a score propagation module to obtain more consistent scores across the student similarity graph. Experiments show that combining automated scoring, expert calibration, and graph-based propagation yields simulated student that more closely track authentication by human judgments. We then analyze which profiles and behaviors are simulated more faithfully, supporting subsequent studies on personalized learning and educational assessment.