# Leveraging generative artificial intelligence to simulate student learning behavior

arXiv: https://arxiv.org/abs/2310.19206 · HTML: https://mlsanity.com/paper/2310.19206/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 27 references that are in the map.
- First posted on arXiv 30 Oct 2023.

## Builds on (most cited first, 5 of 5)

- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Using cognitive psychology to understand GPT-3](https://mlsanity.com/paper/2206.14576/) (2022)
- [Deep Knowledge Tracing](https://mlsanity.com/paper/1506.05908/) (2015)
- [Exploring the Limits of Language Modeling](https://mlsanity.com/paper/1602.02410/) (2016)

## Built on by (most cited first, 16 of 16)

- [Generative Students: Using LLM-Simulated Student Profiles to Support Question Item Evaluation](https://mlsanity.com/paper/2405.11591/) (2024)
- [EduAgent: Generative Student Agents in Learning](https://mlsanity.com/paper/2404.07963/) (2024)
- [Leveraging LLM-Respondents for Item Evaluation: a Psychometric Analysis](https://mlsanity.com/paper/2407.10899/) (2024)
- [EducationQ: Evaluating LLMs' Teaching Capabilities Through Multi-Agent Dialogue Framework](https://mlsanity.com/paper/2504.14928/) (2025)
- [Psychometric Alignment: Capturing Human Knowledge Distributions via Language Models](https://mlsanity.com/paper/2407.15645/) (2024)
- [Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation](https://mlsanity.com/paper/2502.02780/) (2025)
- [Explaining Large Language Models Decisions Using Shapley Values](https://mlsanity.com/paper/2404.01332/) (2024)
- [QG-SMS: Enhancing Test Item Analysis via Student Modeling and Simulation](https://mlsanity.com/paper/2503.05888/) (2025)
- [Closing the Loop: Learning to Generate Writing Feedback via Language Model Simulated Student Revisions](https://mlsanity.com/paper/2410.08058/) (2024)
- [Peer attention enhances student learning](https://mlsanity.com/paper/2312.02358/) (2023)
- [BEAGLE: Behavior-Enforced Agent for Grounded Learner Emulation](https://mlsanity.com/paper/2602.13280/) (2026)
- [SWIM: Student Writing Simulation via Proficiency-Conditioned Generation](https://mlsanity.com/paper/2609.03215/) (2026)
- [Leveraging Interview-Informed LLMs to Model Survey Responses: Comparative Insights from AI-Generated and Human Data](https://mlsanity.com/paper/2505.21997/) (2025)
- [Student Development Agent: Risk-free Simulation for Evaluating AIED Innovations](https://mlsanity.com/paper/2510.09183/) (2025)
- [DiverseClaire: Simulating Students to Improve Introductory Programming Course Materials for All CS1 Learners](https://mlsanity.com/paper/2511.14198/) (2025)
- [Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators](https://mlsanity.com/paper/2605.12748/) (2026)

## Abstract (arXiv)

Student simulation presents a transformative approach to enhance learning outcomes, advance educational research, and ultimately shape the future of effective pedagogy. We explore the feasibility of using large language models (LLMs), a remarkable achievement in AI, to simulate student learning behaviors. Unlike conventional machine learning based prediction, we leverage LLMs to instantiate virtual students with specific demographics and uncover intricate correlations among learning experiences, course materials, understanding levels, and engagement. Our objective is not merely to predict learning outcomes but to replicate learning behaviors and patterns of real students. We validate this hypothesis through three experiments. The first experiment, based on a dataset of N = 145, simulates student learning outcomes from demographic data, revealing parallels with actual students concerning various demographic factors. The second experiment (N = 4524) results in increasingly realistic simulated behaviors with more assessment history for virtual students modelling. The third experiment (N = 27), incorporating prior knowledge and course interactions, indicates a strong link between virtual students' learning behaviors and fine-grained mappings from test questions, course materials, engagement and understanding levels. Collectively, these findings deepen our understanding of LLMs and demonstrate its viability for student simulation, empowering more adaptable curricula design to enhance inclusivity and educational effectiveness.