Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/12587
Title: A teacher-in-the-loop multi-agent framework for transparent essay scoring and feedback
Other Titles: A Teacher-in-the-Loop Multi-Agent Framework for Transparent Essay Scoring and Feedback
Authors: Keramati, Ali
Warschauer, Mark
Keywords: CSCL
Issue Date: 2026
metadata.dc.format.pagerange: 770-772
Publisher: International Society of the Learning Sciences
Citation: Keramati, A. & Warschauer, M. (2026). A teacher-in-the-loop multi-agent framework for transparent essay scoring and feedback. In Rosé, C., Gweon, G., Asterhan, C., & Keune, A. (Eds.), Proceedings of the 19th International Conference on Computer-Supported Collaborative Learning - CSCL 2026 (pp. 770-772). International Society of the Learning Sciences.
Series/Report no.: Proceedings of the 19th International Conference on Computer-Supported Collaborative Learning - CSCL 2026
Abstract: We present MAESF, a multi-agent essay scoring and feedback, as a teacher-centered AI tool for scoring and feedback. The system distributes evaluation across specialized agents and enables educators to interactively query and refine rubric-aligned assessments. Evaluated on the ASAP dataset, MAESF outperforms single-agent baselines and approaches human inter-rater reliability. By combining transparent scoring with teacher-in-the-loop interaction, MAESF reframes automated assessment as a collaborative process that augments teacher capacity and supports more consistent, timely feedback.
Description: POSTER
URI: https://doi.org/10.22318/cscl2026.913900
https://repository.isls.org/handle/1/12587
ISBN: 979-8-9906980-6-2
ISSN: 2543-0157
Appears in Collections:ISLS Annual Meeting 2026

Files in This Item:
File SizeFormat 
CSCL2026_770-772.pdf356.78 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.