Who Am I? History-Aware Profiles for Student Simulation in Tutoring Dialogues
cs.CL, cs.CY
Submitted: 2026-05-28
Updated: 2026-08-30
Comments: Published in EMNLP 2026: The 2026 Conference on Empirical Methods in Natural Language Processing
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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
Terminology
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.
Sources
- Developing Authentic Simulated Learners for Mathematics Teacher Learning: Insights from Three Approaches with Large Language Models
- The Llama 3 Herd of Models
- LoRA: Low-Rank Adaptation of Large Language Models
- Efficient Memory Management for Large Language Model Serving with PagedAttention
- AI tutoring can safely and effectively support students: An exploratory RCT in UK classrooms
- Which Type of Students can LLMs Act? Investigating Authentic Simulation with Graph-based Human-AI Collaborative System
- Explainable Few-shot Knowledge Tracing
- TeachLM: Post-Training LLMs for Education Using Authentic Learning Data
- Simulated Students in Tutoring Dialogues: Substance or Illusion?
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise
- Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based Agents
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering