TY - JOUR
T1 - From Single-Agent System to Multi-Agent System
T2 - Design and Empirical Study on Motivational Learning Activities Supported by LLM-Based Agents
AU - Huang, Changqin
AU - Zhong, Yihua
AU - Wang, Xizhe
AU - Han, Zhongmei
AU - Wei, Tongquan
N1 - Publisher Copyright:
© 2026, Higher Education Press Limited Company. All rights reserved.
PY - 2026/6
Y1 - 2026/6
N2 - The continuous progress in large language models (LLMs) and agent technologies have made LLM-based agents a promising new tool for enhancing the quality and efficiency of teaching and learning in the educational domain. Based on the differences in functional positioning of LLM-based agents, single-agent systems (SASs) are capable of supporting various teaching and learning tasks, such as content generation, intelligent feedback, and assessment. However, due to the homogeneous nature of their interaction characteristics and functional attributes, SASs are confronted with limitations in promoting deeper cognitive development. In contrast, multi-agent systems (MASs) simulate various educational roles, enhancing the diversity and depth of learning interactions and thereby providing more personalized and profound learning experiences. Considering that the application of agents in the learning process primarily relies on learners’ initiative, this study designs motivational learning activities for both SASs and MASs based on the attention, relevance, confidence, and satisfaction (ARCS) model of motivation. To ensure the effective implementation of these activities, a quasi-experimental study is subsequently conducted in the context of English reading. The experimental results reveal that MAS-based motivational learning activities significantly outperform SASs in improving students’ academic achievement in reasoning, evaluation, and application tasks. Furthermore, MASs exhibit a stronger boost in the learning motivation of students and effectively promote deeper cognitive development, particularly in abstraction and generalization skills. This study underscores the value of MASs in supporting in-depth learning and provides insights for further exploration of their applications in education.
AB - The continuous progress in large language models (LLMs) and agent technologies have made LLM-based agents a promising new tool for enhancing the quality and efficiency of teaching and learning in the educational domain. Based on the differences in functional positioning of LLM-based agents, single-agent systems (SASs) are capable of supporting various teaching and learning tasks, such as content generation, intelligent feedback, and assessment. However, due to the homogeneous nature of their interaction characteristics and functional attributes, SASs are confronted with limitations in promoting deeper cognitive development. In contrast, multi-agent systems (MASs) simulate various educational roles, enhancing the diversity and depth of learning interactions and thereby providing more personalized and profound learning experiences. Considering that the application of agents in the learning process primarily relies on learners’ initiative, this study designs motivational learning activities for both SASs and MASs based on the attention, relevance, confidence, and satisfaction (ARCS) model of motivation. To ensure the effective implementation of these activities, a quasi-experimental study is subsequently conducted in the context of English reading. The experimental results reveal that MAS-based motivational learning activities significantly outperform SASs in improving students’ academic achievement in reasoning, evaluation, and application tasks. Furthermore, MASs exhibit a stronger boost in the learning motivation of students and effectively promote deeper cognitive development, particularly in abstraction and generalization skills. This study underscores the value of MASs in supporting in-depth learning and provides insights for further exploration of their applications in education.
KW - ARCS model of motivation
KW - large language model (LLM)
KW - learning in depth (LID)
KW - motivational learning activities
KW - multi-agent system (MAS)
UR - https://www.scopus.com/pages/publications/105046819305
U2 - 10.3868/s110-021-026-0006-5
DO - 10.3868/s110-021-026-0006-5
M3 - 文章
AN - SCOPUS:105046819305
SN - 1673-341X
VL - 21
SP - 105
EP - 125
JO - Frontiers of Education in China
JF - Frontiers of Education in China
IS - 2
ER -