Edu-Theater: A Data-Efficient Agent Framework for Scalable Learner Behavior Simulation through Staging Roll-Call

2026-06-13

AI Summary

This work addresses the high cost, privacy sensitivity, and reliance on sustained participation inherent in collecting large-scale learner behavior data, as well as the computational inefficiency and fragility of existing simulation methods under cold-start conditions. The authors propose a population-aware roll-call simulation paradigm, wherein a teacher agent leverages retrospective roll-call probing to infer individual learner states from population-level ability priors using only a small number of targeted diagnostic queries. This approach introduces the first multi-agent simulation framework that operates without dense individual interaction histories, substantially reducing both data and computational requirements. Experiments on two real-world datasets demonstrate that the method achieves higher simulation accuracy with fewer large language model invocations, and that the resulting synthetic data effectively enhances performance in downstream tasks such as adaptive testing.

Abstract

Large-scale learner-task interaction data are crucial for intelligent educational systems but are costly to collect and constrained by privacy and learner engagement. Learner simulators play a critical role in simulating scalable learner behavior without the need for continuous involvement of real learners. However, existing methods are predominantly \textbf{individual-centric}, pairing a simulator with each learner to iteratively infer latent knowledge states from dense interaction histories, which is both data- and computation-intensive, and fragile in cold-start scenarios. We propose a \textbf{cohort-aware roll-call simulation paradigm} that first constructs cohort-level proficiency priors and refines individual learner states through a small number of targeted diagnostic queries. Based on this paradigm, we introduce \textbf{Edu-Theater}, an LLM-powered agent system that performs cohort-aware learner simulation via a teacher agent and retrospective roll-call probing over learner logs. Edu-Theater enables scalable future behavior simulation without the need for dense per-learner histories. Experiments on two real-world datasets demonstrate that Edu-Theater achieves higher simulation accuracy with significantly fewer LLM calls, producing synthetic data that enhances downstream applications such as adaptive testing.

Problem

• learner simulation
• data efficiency
• cold-start
• cohort-aware
• scalable behavior modeling

Innovation

• cohort-aware simulation
• roll-call probing
• data-efficient learner modeling
• LLM-powered educational agent
• synthetic learner behavior