Since the first instances of online education, where courses were uploaded to accessible and shared online platforms, this form of scaling the dissemination of human knowledge to reach a broader audience has sparked extensive discussion and widespread adoption. Since personalized learning still holds significant potential for improvement, new artificial intelligence (AI) technologies have been continuously integrated into this learning format, resulting in a variety of educational AI applications such as educational recommendation and intelligent tutoring. The emergence of intelligence in large language models (LLMs) has allowed these educational enhancements to be built upon a unified foundational model, enabling deeper integration. In this context, we propose MAIC (Massive AI-Empowered Course), a new form of online education that leverages LLM-driven multi-agent systems to construct an AI-augmented classroom, balancing scalability with adaptivity. Beyond exploring the conceptual framework and technical innovations, we conduct preliminary experiments at Tsinghua University, Beijing, one of the leading universities in China. Drawing from more than 100000 learning records of more than 500 students, we obtain a series of valuable observations and initial analyses. This project will continue to evolve, ultimately aiming to establish a comprehensive open platform that supports and unifies research, technology, and applications to explore the possibilities of online education in the era of large-model AI. We envision this platform as a collaborative hub that brings together educators, researchers, and innovators to collectively explore the future of AI-driven online education.

At present, although generative artificial intelligence provides a possibility for constructing online learning environment that facilitates collaborative interactions among multiple agents, the existing environment construction still faces challenges such as insufficient social presence, lack of cognitive presence, and weak teaching presence. Therefore, this paper analyzed the logical framework of multi-agent collaboration in enhancing the presence in online learning. Meanwhile, it was emphasized in this paper that a positive emotional atmosphere and an inclusive discussion environment should be created through real-time online interactions between multiple agents and humans to enhance social presence, students’ personalized needs should be excavated and teaching strategies should be adaptively adjusted to strengthen teaching presence; and students’ higher-order thinking development should be monitored and assessed in real time using discussions and probing questions to enhance cognitive presence. Based on this, the paper designed a basic paradigm of multi-agent collaboration in online learning environment, constructed an agent platform using large models to develop three types of educational agents: dialogic, analytical, and decision-making. Taking the agent workflow of controlling language as the lead, an interactive classroom system that integrated pre-class preparation, in-class interactions, and post-class assessments within a “human-in-the-loop” framework. Finally, the working/studying modes of teachers and students in multi-agent environment were analyzed, expecting to provide reference for technology-enabled education in the era of multi-agents.