INSIDE the Student’s Mind: Jointly Modeling Latent Reasoning and Action in LLM Student Simulators

LLM-based simulators often reproduce observable actions but fail to capture the underlying reasoning behind them. In education, where student simulation is increasingly used for various applications such as evaluating tutoring systems, this gap is especially pronounced. Two students may submit identical submissions for entirely different reasons. We present INSIDE (Internal Student Dialogue), a framework that fine-tunes Large Language Models (LLMs) not only to act like students but also to think like them. INSIDE generates internal dialogue grounded in Bloom's Taxonomy across cognitive, affective, and action dimensions, and fine-tunes models on paired think traces and action. We baseline against different prompting frameworks and evaluate on two axes: fidelity of simulated actions and quality of generated internal dialogue. Our evaluations show that INSIDE improves simulation fidelity both in terms of action fidelity, matching code generation of real students, and in terms of reasoning alignment, up to 57.9% compared to baselines.