Student simulation with Large language models (LLMs) offers a scalable alternative for educational research and teacher training. Yet, its validity depends on whether models maintain stable personas across extended interactions. We test this prerequisite using a dual-assessment framework measuring self-reported characteristics and observer-rated behavioral expressions. Across two experiments testing four clinically-grounded ADHD persona conditions, five LLMs, and three prompt designs, we quantify between-conversation stability (N=4,968) and within-conversation stability (N=3,952 across 9 turns). Self-reported characteristics remain stable for high intensities, constituting a necessary prerequisite for valid behavioral simulation. Observer-rated behavioral expression reveals selective instability: within-conversation drift occurs in unscripted dialog for high and moderate ADHD personas. Scripted interactions with explicit task prompts eliminate this drift entirely. Stable, persona-aligned simulated learners benefit from a structured interaction design to maintain behavioral coherence, which holds significant implications for teacher training, adaptive tutoring, and any application requiring sustained, path-dependent learner interactions.
@article{arxiv.2605.06307,
title = {LLM-Based Educational Simulation: Evaluating Temporal Student Persona Stability Across ADHD Profiles},
author = {Jana Gonnermann-Müller and Jennifer Haase and Nicolas Leins and Thomas Kosch and Sebastian Pokutta},
journal= {arXiv preprint arXiv:2605.06307},
year = {2026}
}