Constructing High-presence Online Learning Environment via Multi-Agent Collaborative Interaction

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.