---
source_url: https://arxiv.org/abs/2409.03512
ingested: 2026-05-07
sha256: 7fb5c6dff60080a1b3cbd20fbab1665be157d0474dc4270217da636ffce72327
---
# From MOOC to MAIC: Reshaping Online Teaching and Learning through LLM-driven Agents

**Authors:** Jifan Yu, Zheyuan Zhang, Daniel Zhang-li, Shangqing Tu, Zhanxin Hao, Rui Miao Li, Haoxuan Li, Yuanchun Wang, Hanming Li, Linlu Gong, Jie Cao, Jiayin Lin, Jinchang Zhou, Fei Qin, Haohua Wang, Jianxiao Jiang, Lijun Deng, Yisi Zhan, Chaojun Xiao, Xusheng Dai, Xuan Yan, Nianyi Lin, Nan Zhang, Ruixin Ni, Yang Dang, Lei Hou, Yu Zhang, Xu Han, Manli Li, Juanzi Li, Zhiyuan Liu, Huiqin Liu, Maosong Sun (33 authors)  
**arXiv:** 2409.03512  
**Submitted:** 5 Sep 2024

## Core Concept

MAIC (Massive AI-empowered Course) is a new form of online education that leverages LLM-driven multi-agent systems to construct an AI-augmented classroom, balancing scalability with adaptivity.

### What is MAIC?
- Massive AI-empowered Course — the next evolution from MOOCs
- Built on LLM-driven multi-agent systems that function as an AI-augmented classroom
- Moves beyond fragmented EdAI tools (recommendation engines, traditional ITS) by unifying capabilities on a single foundational model
- Explicitly designed to balance massive scalability with personalized adaptivity

## Preliminary Experimental Results

Initial deployment at Tsinghua University:
- Students: >500
- Learning records: >100,000
- Outcome: A series of valuable observations and initial analyses supporting the MAIC framework

## Vision & Roadmap

- Immediate focus: Continue iterating on the conceptual framework and technical innovations based on experimental feedback
- Ultimate aim: Establish a comprehensive open platform that supports and unifies research, technology, and applications for AI-driven online education
- Community goal: Serve as a collaborative hub bringing together educators, researchers, and innovators to collectively define the future of online education in the large-model AI era