Search papers, labs, and topics across Lattice.
EducaSim is introduced as a novel framework using generative agents to simulate small-group instructional sections, enabling teachers-in-training to practice instruction at scale. It employs diverse pedagogical personas, course material, and agent-based architectures to create a rich role-play environment. Initial experiences in a CS1 course with 20,000 students showed teachers found it to be a positive experience, suggesting potential for scalable experiential teaching practice.
Imagine a flight simulator, but for teaching: EducaSim lets CS1 instructors hone their skills in a realistic, scalable environment powered by generative agents.
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.
Stanford HAI