Rubrics-enhanced multi-agent system based on LLM for teaching behavior assessment: Design and application.
Saved in:
| Title: | Rubrics-enhanced multi-agent system based on LLM for teaching behavior assessment: Design and application. |
|---|---|
| Authors: | Niu, Juan1 2023200348@snnu.edu.cn, He, Xiuqin2 xiuqing@snnu.edu.cn, Wang, Xu1 mitm0829@snnu.edu.cn, Han, Guangxin1 hgx@snnu.edu.cn, He, Juhou1 juhouh@snnu.edu.cn |
| Source: | Educational Technology & Society. Apr2026, Vol. 29 Issue 2, p270-296. 27p. |
| Subject Terms: | *Scoring rubrics, *Behavioral assessment, *Psychological feedback, *Educational technology, *Teacher development, Multiagent systems, Language models |
| Abstract: | Consistent feedback and accurate assessments are essential for teachers’ professional development; however, the scarcity of experts often prevents teachers from receiving timely and targeted assessments in teaching practice. The emergence of multi-agent systems based on Large Language Models (LLMs) offers a promising solution to this challenge with its flexible collaboration mechanism. We developed a rubric-enhanced multi-agent system for assessing teaching behaviors, designated as AI-TBAS (AI-driven Teaching Behavior Assessment System), which encompasses the processes of rubric development, preprocessing of teaching video data, and the construction of a multi-agent system. The evaluation results of revealed that rubrics enhance the performance of AI-TBAS, and the outputs of its multi-agent framework outperformed those of the single-agent framework, aligning more closely with expert assessments. The findings of the empirical study involving 30 teachers illustrate that AI-TBAS can offer personalized feedback on teaching behaviors. Additionally, an investigation revealed that both teachers and students perceived the AI-TBAS as beneficial for improving teaching practices, exhibiting a positive attitude towards its implementation. [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 |
| FullText | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: ehh DbLabel: Education Research Complete An: 192828634 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Rubrics-enhanced multi-agent system based on LLM for teaching behavior assessment: Design and application. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Niu%2C+Juan%22">Niu, Juan</searchLink><relatesTo>1</relatesTo><i> 2023200348@snnu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22He%2C+Xiuqin%22">He, Xiuqin</searchLink><relatesTo>2</relatesTo><i> xiuqing@snnu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Wang%2C+Xu%22">Wang, Xu</searchLink><relatesTo>1</relatesTo><i> mitm0829@snnu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Han%2C+Guangxin%22">Han, Guangxin</searchLink><relatesTo>1</relatesTo><i> hgx@snnu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22He%2C+Juhou%22">He, Juhou</searchLink><relatesTo>1</relatesTo><i> juhouh@snnu.edu.cn</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Educational+Technology+%26+Society%22">Educational Technology & Society</searchLink>. Apr2026, Vol. 29 Issue 2, p270-296. 27p. – Name: Subject Label: Subject Terms Group: Su Data: *<searchLink fieldCode="DE" term="%22Scoring+rubrics%22">Scoring rubrics</searchLink><br />*<searchLink fieldCode="DE" term="%22Behavioral+assessment%22">Behavioral assessment</searchLink><br />*<searchLink fieldCode="DE" term="%22Psychological+feedback%22">Psychological feedback</searchLink><br />*<searchLink fieldCode="DE" term="%22Educational+technology%22">Educational technology</searchLink><br />*<searchLink fieldCode="DE" term="%22Teacher+development%22">Teacher development</searchLink><br /><searchLink fieldCode="DE" term="%22Multiagent+systems%22">Multiagent systems</searchLink><br /><searchLink fieldCode="DE" term="%22Language+models%22">Language models</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Consistent feedback and accurate assessments are essential for teachers’ professional development; however, the scarcity of experts often prevents teachers from receiving timely and targeted assessments in teaching practice. The emergence of multi-agent systems based on Large Language Models (LLMs) offers a promising solution to this challenge with its flexible collaboration mechanism. We developed a rubric-enhanced multi-agent system for assessing teaching behaviors, designated as AI-TBAS (AI-driven Teaching Behavior Assessment System), which encompasses the processes of rubric development, preprocessing of teaching video data, and the construction of a multi-agent system. The evaluation results of revealed that rubrics enhance the performance of AI-TBAS, and the outputs of its multi-agent framework outperformed those of the single-agent framework, aligning more closely with expert assessments. The findings of the empirical study involving 30 teachers illustrate that AI-TBAS can offer personalized feedback on teaching behaviors. Additionally, an investigation revealed that both teachers and students perceived the AI-TBAS as beneficial for improving teaching practices, exhibiting a positive attitude towards its implementation. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>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.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=ehh&AN=192828634 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.30191/ETS.202604_29(2).SP04 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 27 StartPage: 270 Subjects: – SubjectFull: Scoring rubrics Type: general – SubjectFull: Behavioral assessment Type: general – SubjectFull: Psychological feedback Type: general – SubjectFull: Educational technology Type: general – SubjectFull: Teacher development Type: general – SubjectFull: Multiagent systems Type: general – SubjectFull: Language models Type: general Titles: – TitleFull: Rubrics-enhanced multi-agent system based on LLM for teaching behavior assessment: Design and application. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Niu, Juan – PersonEntity: Name: NameFull: He, Xiuqin – PersonEntity: Name: NameFull: Wang, Xu – PersonEntity: Name: NameFull: Han, Guangxin – PersonEntity: Name: NameFull: He, Juhou IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 04 Text: Apr2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 11763647 Numbering: – Type: volume Value: 29 – Type: issue Value: 2 Titles: – TitleFull: Educational Technology & Society Type: main |
| ResultId | 1 |
