Enhancing Online Learning Through Multi-Agent Debates for CS University Students
As recent advancements in large language models enhance reasoning across various domains, educators are increasingly exploring their use in conversation-based tutoring systems. However, since LLMs are black-box models to users and lack human-like problem-solving strategies, users are hardly convince...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/11/5877 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850128887822942208 |
|---|---|
| author | Jing Du Guangtao Xu Wenhao Liu Dibin Zhou Fuchang Liu |
| author_facet | Jing Du Guangtao Xu Wenhao Liu Dibin Zhou Fuchang Liu |
| author_sort | Jing Du |
| collection | DOAJ |
| description | As recent advancements in large language models enhance reasoning across various domains, educators are increasingly exploring their use in conversation-based tutoring systems. However, since LLMs are black-box models to users and lack human-like problem-solving strategies, users are hardly convinced by the answers provided by LLMs. This lack of trust can potentially undermine the effectiveness of learning in educational scenarios. To address these issues, we introduce a novel approach that integrates multi-agent debates into a lecture video Q&A system, aiming to assist computer science (CS) university students in self-learning by using LLMs to simulate debates between affirmative and negative debaters and a judge to reach a final answer and presenting the entire process to users for review. This approach is expected to lead to better learning outcomes and the improvement of students’ critical thinking. To validate the effectiveness of this approach, we carried out a user study through a prototype system and conducted preliminary experiments based on video lecture learning involving 90 CS students from three universities. The study compared different conditions and demonstrated that students who had access to a combination of video-based Q&A and multi-agent debates performed significantly better on quizzes compared to those who only had access to the video or video-based Q&A. These findings indicate that integrating multi-agent debates with lecture videos can substantially enhance the learning experience, which is also beneficial for the development of students’ high-order thinking abilities in the future. |
| format | Article |
| id | doaj-art-c69cfe28b91e42b284ba08c717bf9d45 |
| institution | OA Journals |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-c69cfe28b91e42b284ba08c717bf9d452025-08-20T02:33:09ZengMDPI AGApplied Sciences2076-34172025-05-011511587710.3390/app15115877Enhancing Online Learning Through Multi-Agent Debates for CS University StudentsJing Du0Guangtao Xu1Wenhao Liu2Dibin Zhou3Fuchang Liu4Department of Media and Communication, Kangwon National University, Chuncheon 24341, Republic of KoreaJing Hengyi School of Education, Hangzhou Normal University, Hangzhou 311121, ChinaSchool of Information Science and Technology, Hangzhou Normal University, Hangzhou 311121, ChinaSchool of Information Science and Technology, Hangzhou Normal University, Hangzhou 311121, ChinaSchool of Information Science and Technology, Hangzhou Normal University, Hangzhou 311121, ChinaAs recent advancements in large language models enhance reasoning across various domains, educators are increasingly exploring their use in conversation-based tutoring systems. However, since LLMs are black-box models to users and lack human-like problem-solving strategies, users are hardly convinced by the answers provided by LLMs. This lack of trust can potentially undermine the effectiveness of learning in educational scenarios. To address these issues, we introduce a novel approach that integrates multi-agent debates into a lecture video Q&A system, aiming to assist computer science (CS) university students in self-learning by using LLMs to simulate debates between affirmative and negative debaters and a judge to reach a final answer and presenting the entire process to users for review. This approach is expected to lead to better learning outcomes and the improvement of students’ critical thinking. To validate the effectiveness of this approach, we carried out a user study through a prototype system and conducted preliminary experiments based on video lecture learning involving 90 CS students from three universities. The study compared different conditions and demonstrated that students who had access to a combination of video-based Q&A and multi-agent debates performed significantly better on quizzes compared to those who only had access to the video or video-based Q&A. These findings indicate that integrating multi-agent debates with lecture videos can substantially enhance the learning experience, which is also beneficial for the development of students’ high-order thinking abilities in the future.https://www.mdpi.com/2076-3417/15/11/5877online learningmulti-agentlarge language models |
| spellingShingle | Jing Du Guangtao Xu Wenhao Liu Dibin Zhou Fuchang Liu Enhancing Online Learning Through Multi-Agent Debates for CS University Students Applied Sciences online learning multi-agent large language models |
| title | Enhancing Online Learning Through Multi-Agent Debates for CS University Students |
| title_full | Enhancing Online Learning Through Multi-Agent Debates for CS University Students |
| title_fullStr | Enhancing Online Learning Through Multi-Agent Debates for CS University Students |
| title_full_unstemmed | Enhancing Online Learning Through Multi-Agent Debates for CS University Students |
| title_short | Enhancing Online Learning Through Multi-Agent Debates for CS University Students |
| title_sort | enhancing online learning through multi agent debates for cs university students |
| topic | online learning multi-agent large language models |
| url | https://www.mdpi.com/2076-3417/15/11/5877 |
| work_keys_str_mv | AT jingdu enhancingonlinelearningthroughmultiagentdebatesforcsuniversitystudents AT guangtaoxu enhancingonlinelearningthroughmultiagentdebatesforcsuniversitystudents AT wenhaoliu enhancingonlinelearningthroughmultiagentdebatesforcsuniversitystudents AT dibinzhou enhancingonlinelearningthroughmultiagentdebatesforcsuniversitystudents AT fuchangliu enhancingonlinelearningthroughmultiagentdebatesforcsuniversitystudents |