Jina Kang

Can LLMs Reliably Simulate Human Learner Actions? A Simulation Authoring Framework for Open-Ended Learning Environments

2025 · Proceedings of the AAAI Conference on Artificial Intelligence

Simulating learner actions helps stress-test open-ended interactive learning environments and prototype new adaptations before deployment. While recent studies show the promise of using large language models (LLMs) for simulating human behavior, such approaches have not …