EducaSim: Interactive Simulacra for CS1 Instructional Practice

TL;DR

EducaSim is an innovative framework that employs generative agents to simulate classroom environments, enabling scalable, role-play-based training for novice teachers in large online courses without extensive personnel requirements.

Contribution

This work introduces EducaSim, a novel agent-based simulation platform that facilitates scalable, pedagogically rich teacher training in CS1 courses, addressing scalability challenges of traditional role play.

Findings

Teachers found EducaSim to be a positive learning experience.

The framework was successfully used in a six-week CS1 course with 20,000 students.

EducaSim enables scalable teacher training without high personnel costs.

Abstract

Role play is a high-impact mode of training that has demonstrated its effectiveness in improving learning outcomes. However, it is difficult to scale to teacher instruction due to its inherent dependency on providing personnel who are both trained and available to facilitate this learning environment. This poses a challenge, especially to massive online courses which may employ and aid hundreds to thousands of novice teachers. In this work, we present EducaSim: a novel framework that uses generative agents to simulate a small-group section for teachers-in-training to practice instruction. EducaSim works by implementing diverse pedagogical-based personas, actual course material, and agent-based architectures constructed for instructional practice to provide a pedagogically rich environment for teachers-in-training to engage in role play learning -- without the costly overhead that comes with it. We share our experiences with constructing and making the tool available for experimental training and preparation in a six-week CS1 course supporting 20,000 students. We found that teachers who engaged generally saw it as a positive experience. We believe that EducaSim is an important step to providing experiential teaching practice at scale for closely-defined settings and has great potential for future applications.