The design and application of RAG-based conversational agents for collaborative problem solving

Xuanyan ZHONG, Haiyang XIN, Wenfeng LI, Zehui ZHAN, May Hung May CHENG

Research output: Chapter in Book/Report/Conference proceedingChapters

1 Citation (Scopus)

Abstract

Dialogue is the basis of collaborative problem solving, and the development of generative artificial intelligence has made dialogue no longer limited to human-to-human, and human-computer dialogue has gradually become an important way for people to solve problems. At the same time, with the change of the subject of collaborative problem solving, the cultivation of collaborative problem-solving skill urgently needs to explore a new path. In this regard, more and more studies have begun to apply conversational agents in collaborative problem-solving activities, digging deeper into the effects of time on students in conversational agents. However, there is no clear answer to the question of how conversational agents can be better integrated into a collaborative environment for all to assist people in the collaborative problem-solving process and improve performance. In this study, we constructed a conceptual model of human-computer collaboration in order to improve students' learning performance. Based on this model, we integrated Retrieval-Augmented Generative and GPT to construct a conversational agent, and the results of the study showed that the Retrieval-Augmented Generative Agent for Collaborative Problem Solving constructed in this study can effectively promote students' collaborative problem-solving performance. Copyright © 2024 held by the owner/author(s).

Original languageEnglish
Title of host publicationProceedings of the 2024 9th International Conference on Distance Education and Learning (ICDEL 2024)
Place of PublicationNew York
PublisherAssociation for Computing Machinery
Pages62-68
ISBN (Electronic)9798400716805
DOIs
Publication statusPublished - Aug 2024

Citation

Zhong, X., Xin, H., Li, W., Zhan, Z., & Cheng, M.-H. (2024). The design and application of RAG-based conversational agents for collaborative problem solving. In Proceedings of the 2024 9th International Conference on Distance Education and Learning (ICDEL 2024) (pp. 62-68). Association for Computing Machinery. https://doi.org/10.1145/3675812.3675871

Keywords

  • Conversational agent
  • Collaborative problem solving
  • GPT

Fingerprint

Dive into the research topics of 'The design and application of RAG-based conversational agents for collaborative problem solving'. Together they form a unique fingerprint.