Evaluating Learning States in Synchronous Remote Classes via Qwen2.5-Max with RAG and ReAct Agent

Haoyuan He; Bemnet Wondimagegnehu Mersha; Yaping Dai; Kaoru Hirota; Wei Dai; Yumin Lin

doi:10.1007/978-981-95-6730-0_10

Evaluating Learning States in Synchronous Remote Classes via Qwen2.5-Max with RAG and ReAct Agent

Haoyuan He
, Bemnet Wondimagegnehu Mersha^*
, Yaping Dai
, Kaoru Hirota
, Wei Dai
, Yumin Lin

^*Corresponding author for this work

School of Automation

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In a synchronous remote class, where lectures are simultaneously delivered to both local and remote students, evaluating the group learning state of the remote class presents significant challenges. To address this problem, a series of methods for evaluating students’ learning states in the synchronous remote class based on Qwen2.5-Max is proposed. First, a behavior recognition model and a facial emotion recognition model were constructed to recognize each student’s actions and facial emotions in the class. Subsequently, Qwen2.5-Max with the RAG individual learning state recognition method is proposed. Finally, Qwen2.5-Max with ReAct agent for the synchronous remote class group learning state recognition method is proposed to determine the group learning state and provide instructional suggestions to the teacher. The proposed methods are tested using a custom-made dataset. The results indicate that the methods can help teachers balance local and remote classes by enhancing the quality of synchronous remote teaching.

Original language	English
Title of host publication	Advanced Computational Intelligence and Intelligent Informatics - 9th International Workshop, IWACIII 2025, Proceedings
Editors	Hongbin Ma, Bin Xin, Jinhua She, Yaping Dai
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	135-150
Number of pages	16
ISBN (Print)	9789819567294
DOIs	https://doi.org/10.1007/978-981-95-6730-0_10
Publication status	Published - 2026
Event	9th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2025 - Zhuhai, China Duration: 31 Oct 2025 → 4 Nov 2025

Publication series

Name	Communications in Computer and Information Science
Volume	2780 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	9th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2025
Country/Territory	China
City	Zhuhai
Period	31/10/25 → 4/11/25

Keywords

Qwen2.5-Max
RAG
ReAct Agent
Synchronous Remote Class

Access to Document

10.1007/978-981-95-6730-0_10

Cite this

He, H., Mersha, B. W., Dai, Y., Hirota, K., Dai, W., & Lin, Y. (2026). Evaluating Learning States in Synchronous Remote Classes via Qwen2.5-Max with RAG and ReAct Agent. In H. Ma, B. Xin, J. She, & Y. Dai (Eds.), Advanced Computational Intelligence and Intelligent Informatics - 9th International Workshop, IWACIII 2025, Proceedings (pp. 135-150). (Communications in Computer and Information Science; Vol. 2780 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-95-6730-0_10

He, Haoyuan ; Mersha, Bemnet Wondimagegnehu ; Dai, Yaping et al. / Evaluating Learning States in Synchronous Remote Classes via Qwen2.5-Max with RAG and ReAct Agent. Advanced Computational Intelligence and Intelligent Informatics - 9th International Workshop, IWACIII 2025, Proceedings. editor / Hongbin Ma ; Bin Xin ; Jinhua She ; Yaping Dai. Springer Science and Business Media Deutschland GmbH, 2026. pp. 135-150 (Communications in Computer and Information Science).

@inproceedings{01ac8fcd147e4169ae735d411bc29605,

title = "Evaluating Learning States in Synchronous Remote Classes via Qwen2.5-Max with RAG and ReAct Agent",

abstract = "In a synchronous remote class, where lectures are simultaneously delivered to both local and remote students, evaluating the group learning state of the remote class presents significant challenges. To address this problem, a series of methods for evaluating students{\textquoteright} learning states in the synchronous remote class based on Qwen2.5-Max is proposed. First, a behavior recognition model and a facial emotion recognition model were constructed to recognize each student{\textquoteright}s actions and facial emotions in the class. Subsequently, Qwen2.5-Max with the RAG individual learning state recognition method is proposed. Finally, Qwen2.5-Max with ReAct agent for the synchronous remote class group learning state recognition method is proposed to determine the group learning state and provide instructional suggestions to the teacher. The proposed methods are tested using a custom-made dataset. The results indicate that the methods can help teachers balance local and remote classes by enhancing the quality of synchronous remote teaching.",

keywords = "Qwen2.5-Max, RAG, ReAct Agent, Synchronous Remote Class",

author = "Haoyuan He and Mersha, \{Bemnet Wondimagegnehu\} and Yaping Dai and Kaoru Hirota and Wei Dai and Yumin Lin",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.; 9th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2025 ; Conference date: 31-10-2025 Through 04-11-2025",

year = "2026",

doi = "10.1007/978-981-95-6730-0\_10",

language = "English",

isbn = "9789819567294",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "135--150",

editor = "Hongbin Ma and Bin Xin and Jinhua She and Yaping Dai",

booktitle = "Advanced Computational Intelligence and Intelligent Informatics - 9th International Workshop, IWACIII 2025, Proceedings",

address = "Germany",

}

He, H, Mersha, BW, Dai, Y , Hirota, K, Dai, W & Lin, Y 2026, Evaluating Learning States in Synchronous Remote Classes via Qwen2.5-Max with RAG and ReAct Agent. in H Ma, B Xin, J She & Y Dai (eds), Advanced Computational Intelligence and Intelligent Informatics - 9th International Workshop, IWACIII 2025, Proceedings. Communications in Computer and Information Science, vol. 2780 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 135-150, 9th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2025, Zhuhai, China, 31/10/25. https://doi.org/10.1007/978-981-95-6730-0_10

Evaluating Learning States in Synchronous Remote Classes via Qwen2.5-Max with RAG and ReAct Agent. / He, Haoyuan; Mersha, Bemnet Wondimagegnehu; Dai, Yaping et al.
Advanced Computational Intelligence and Intelligent Informatics - 9th International Workshop, IWACIII 2025, Proceedings. ed. / Hongbin Ma; Bin Xin; Jinhua She; Yaping Dai. Springer Science and Business Media Deutschland GmbH, 2026. p. 135-150 (Communications in Computer and Information Science; Vol. 2780 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Evaluating Learning States in Synchronous Remote Classes via Qwen2.5-Max with RAG and ReAct Agent

AU - He, Haoyuan

AU - Mersha, Bemnet Wondimagegnehu

AU - Dai, Yaping

AU - Hirota, Kaoru

AU - Dai, Wei

AU - Lin, Yumin

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.

PY - 2026

Y1 - 2026

N2 - In a synchronous remote class, where lectures are simultaneously delivered to both local and remote students, evaluating the group learning state of the remote class presents significant challenges. To address this problem, a series of methods for evaluating students’ learning states in the synchronous remote class based on Qwen2.5-Max is proposed. First, a behavior recognition model and a facial emotion recognition model were constructed to recognize each student’s actions and facial emotions in the class. Subsequently, Qwen2.5-Max with the RAG individual learning state recognition method is proposed. Finally, Qwen2.5-Max with ReAct agent for the synchronous remote class group learning state recognition method is proposed to determine the group learning state and provide instructional suggestions to the teacher. The proposed methods are tested using a custom-made dataset. The results indicate that the methods can help teachers balance local and remote classes by enhancing the quality of synchronous remote teaching.

AB - In a synchronous remote class, where lectures are simultaneously delivered to both local and remote students, evaluating the group learning state of the remote class presents significant challenges. To address this problem, a series of methods for evaluating students’ learning states in the synchronous remote class based on Qwen2.5-Max is proposed. First, a behavior recognition model and a facial emotion recognition model were constructed to recognize each student’s actions and facial emotions in the class. Subsequently, Qwen2.5-Max with the RAG individual learning state recognition method is proposed. Finally, Qwen2.5-Max with ReAct agent for the synchronous remote class group learning state recognition method is proposed to determine the group learning state and provide instructional suggestions to the teacher. The proposed methods are tested using a custom-made dataset. The results indicate that the methods can help teachers balance local and remote classes by enhancing the quality of synchronous remote teaching.

KW - Qwen2.5-Max

KW - RAG

KW - ReAct Agent

KW - Synchronous Remote Class

UR - https://www.scopus.com/pages/publications/105030923754

U2 - 10.1007/978-981-95-6730-0_10

DO - 10.1007/978-981-95-6730-0_10

M3 - Conference contribution

AN - SCOPUS:105030923754

SN - 9789819567294

T3 - Communications in Computer and Information Science

SP - 135

EP - 150

BT - Advanced Computational Intelligence and Intelligent Informatics - 9th International Workshop, IWACIII 2025, Proceedings

A2 - Ma, Hongbin

A2 - Xin, Bin

A2 - She, Jinhua

A2 - Dai, Yaping

PB - Springer Science and Business Media Deutschland GmbH

T2 - 9th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2025

Y2 - 31 October 2025 through 4 November 2025

ER -

He H, Mersha BW, Dai Y , Hirota K, Dai W, Lin Y. Evaluating Learning States in Synchronous Remote Classes via Qwen2.5-Max with RAG and ReAct Agent. In Ma H, Xin B, She J, Dai Y, editors, Advanced Computational Intelligence and Intelligent Informatics - 9th International Workshop, IWACIII 2025, Proceedings. Springer Science and Business Media Deutschland GmbH. 2026. p. 135-150. (Communications in Computer and Information Science). doi: 10.1007/978-981-95-6730-0_10