The paper introduces SimClass, a multi-agent classroom simulation framework that leverages large language models (LLMs) to simulate real classroom interactions with user participation. The authors address several key research questions, including the simulation capability of LLMs in multi-agent classrooms, the measurement of learning experiences, and the emergence of group behaviors. They design representative class roles and introduce a novel class control mechanism to manage classroom interactions. Experiments conducted in two real-world courses with 48 students demonstrate that SimClass effectively simulates traditional classroom interactions, enhances user engagement, and improves learning experiences. The framework also exhibits emergent group behaviors, such as collaborative teaching and emotional support, which enrich the classroom environment. The study concludes by highlighting the potential of LLM-empowered multi-agent systems in virtual classroom teaching and the release of the dataset for further research.The paper introduces SimClass, a multi-agent classroom simulation framework that leverages large language models (LLMs) to simulate real classroom interactions with user participation. The authors address several key research questions, including the simulation capability of LLMs in multi-agent classrooms, the measurement of learning experiences, and the emergence of group behaviors. They design representative class roles and introduce a novel class control mechanism to manage classroom interactions. Experiments conducted in two real-world courses with 48 students demonstrate that SimClass effectively simulates traditional classroom interactions, enhances user engagement, and improves learning experiences. The framework also exhibits emergent group behaviors, such as collaborative teaching and emotional support, which enrich the classroom environment. The study concludes by highlighting the potential of LLM-empowered multi-agent systems in virtual classroom teaching and the release of the dataset for further research.