aiqbench analysis
This research advances automated tutoring systems by introducing history-conditioned student simulation, where LLMs leverage past learning interactions to generate more faithful persona profiles via reinforcement learning. By grounding simulations in longitudinal data rather than isolated dialogue turns, the method significantly improves the evaluation and training of AI-driven educational tools. The work highlights a critical shift toward context-aware modeling that better captures the nuances of student behavior over time.
Who Am I? History-Aware Profiles for Student Simulation in Tutoring Dialogues
arXiv:2605.30051v2 Announce Type: replace Abstract: A key part of developing large language model (LLM)-powered, automated tutoring tools is student simulation, i.e., using LLMs to role-play as students, which can facilitate tutor model evaluation and training. Existing work mostly focuses on within-dialogue simulation, which lacks context on student knowledge and behavior, partly due to not grounding in past student question-answering or dialogue interactions. In this work, we introduce the task of history-conditioned student simulation, where the goal is to accurately predict student dialogue turns by leveraging information in the student's learning history. We propose a two-component framework in which a profile generator summarizes a student's history and a simulator predicts student turns conditioned on the resulting profile. We train both components with reinforcement learning (RL), yielding profiles optimized for faithful student simulation. We evaluate our method and baselines on the first-of-its-kind real-world dataset of student dialogues and question responses that we collect from a math learning platform. Extensive experiments show that our method significantly outperforms baselines, and demonstrate the importance of history, profiles, and RL training.
Title:Who Am I? History-Aware Profiles for Student Simulation in Tutoring Dialogues
Abstract:A key part of developing large language model (LLM)-powered, automated tutoring tools is student simulation, i.e., using LLMs to role-play as students, which can facilitate tutor model evaluation and training. Existing work mostly focuses on within-dialogue simulation, which lacks context on student knowledge and behavior, partly due to not grounding in past student question-answering or dialogue interactions. In this work, we introduce the task of history-conditioned student simulation, where the goal is to accurately predict student dialogue turns by leveraging information in the student's learning history. We propose a two-component framework in which a profile generator summarizes a student's history and a simulator predicts student turns conditioned on the resulting profile. We train both components with reinforcement learning (RL), yielding profiles optimized for faithful student simulation. We evaluate our method and baselines on the first-of-its-kind real-world dataset of student dialogues and question responses that we collect from a math learning platform. Extensive experiments show that our method significantly outperforms baselines, and demonstrate the importance of history, profiles, and RL training.
Computation and Language (cs.CL); Computers and Society (cs.CY)
arXiv:2605.30051 [cs.CL]
(or arXiv:2605.30051v2 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2605.30051 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 278 words
Related coverage
The First Chatbot’s Multiple Personalities
IEEE Spectrum · Jul 15, 2026
HACHIMI-II: From Role-Play to Learner Behavior Modeling for Faithful Student Simulation
arXiv · Oct 15, 2026
AI by Default
LessWrong · Oct 17, 2026
Facial-Expression-Aware Prompting for Empathetic LLM Tutoring
arXiv · Jul 31, 2026