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

2026-08-11

AI Summary

Current large language model–based student simulators predominantly replicate observable behaviors and struggle to capture underlying cognitive and affective processes. To address this limitation, this work proposes the INTERNAL STUDENT DIALOGUE (INSIDE) framework, which introduces Bloom’s taxonomy into student modeling for the first time. By fine-tuning a large language model, INSIDE simultaneously generates internal dialogues across three dimensions—cognition, emotion, and action—and jointly aligns these mental trajectories with behavioral outputs. This approach substantially enhances the realism and interpretability of simulated learners. Empirical evaluation on code generation tasks demonstrates a reasoning alignment rate of 57.9%, outperforming existing methods.

Abstract

Large Language Model (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 INTERNAL STUDENT DIALOGUE (INSIDE), a student modeling framework that fine-tunes 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 actions. 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 in both action fidelity, matching code generation of real students, and reasoning alignment, achieving the highest alignment across models up to 57.9%.

Problem

• student simulation
• latent reasoning
• large language models
• cognitive modeling
• internal dialogue

Innovation

• student simulation
• internal dialogue
• reasoning modeling
• Bloom's Taxonomy
• LLM fine-tuning