Promoting problem-solving skills in computer programming with an LLM-empowered multi-agent system: A cognitive apprenticeship perspective.
Saved in:
| Title: | Promoting problem-solving skills in computer programming with an LLM-empowered multi-agent system: A cognitive apprenticeship perspective. |
|---|---|
| Authors: | Wang, Xiaochun1 wang_xiaochun@sohu.com, Li, Jingze1 ljz990317@163.com, Gu, Qirui1 2275845126@qq.com, Liang, Deming2 ldm_cnu2014@163.com |
| Source: | Educational Technology & Society. Apr2026, Vol. 29 Issue 2, p355-374. 20p. |
| Subject Terms: | *Computer programming, *Computer programming education, *Problem solving, *Cognitive training, *Educational technology, Multiagent systems, Language models |
| Abstract: | To address the limitations of large language models in fostering problem-solving skills in programming, this paper proposes an LLM-empowered multi-agent system grounded in a theoretical framework that integrates cognitive apprenticeship with the Use-Modify-Create programming learning model. Employing a mixed-methods research approach, the study provides a preliminary investigation into the potential of such systems to support the development of programming problem-solving skills. Findings indicate that the LLMempowered multi-agent system can effectively facilitate problem-solving learning in computer programming, simulate the instructional process for programming problem-solving based on cognitive apprenticeship, and reduce the extraneous cognitive load associated with prompt engineering. Moreover, students in the experimental group expressed favorable attitudes and a willingness to continue using the system. This research offers a promising solution to the challenge of insufficient instructor guidance in programming education and lays the groundwork for exploring the role of LLM-empowered multi-agent systems in supporting or assuming certain instructional functions. [ABSTRACT FROM AUTHOR] |
| Copyright of Educational Technology & Society is the property of International Forum of Educational Technology & Society (IFETS) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Education Research Complete |
Be the first to leave a comment!
