Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/11884
Full metadata record
DC FieldValueLanguage
dc.contributor.authorWang, Yu
dc.contributor.authorBergner, Yoav
dc.date.accessioned2025-06-13T03:01:00Z-
dc.date.available2025-06-12T22:54:42Z
dc.date.available2025-06-13T03:01:00Z-
dc.date.issued2025
dc.identifier.citationWang, Y. & Bergner, Y. (2025). Number of Players, Zero: Using Multi-Agent Collaboration to Evaluate Unsolvable Collaborative Items. In Oshima, J., Chen, B., Vogel, F., & Järvelä, J. (Eds.), Proceedings of the 18th International Conference on Computer-Supported Collaborative Learning - CSCL 2025 (pp. 409-414). International Society of the Learning Sciences.en
dc.identifier.urihttps://doi.org/10.22318/cscl2025.325936
dc.identifier.urihttps://repository.isls.org//handle/1/11884-
dc.descriptionShort Paperen
dc.description.abstractWhile the importance of collaborative problem-solving (CPS) is widely acknowledged, developing and evaluating CPS items remains challenging. This study extends to multi-agent systems (MASs) prior work on CPS item templates and the use of large language models for evaluation of collaborative interdependence in math problems designed for two solvers working together. Specifically, we test the hypothesis that MASs more accurately handle evaluation of flawed items that are unsolvable even if both students collaborate with respect to the information and/or answer affordances provided to them.en
dc.format.extent409-414en
dc.publisherInternational Society of the Learning Sciences
dc.relation.ispartofurn:ISBN:979-8-9906980-4-8
dc.relation.ispartofProceedings of the 18th International Conference on Computer-Supported Collaborative Learning - CSCL 2025, pp. 409-414
dc.relation.ispartofseriesProceedings of the 18th International Conference on Computer-Supported Collaborative Learning - CSCL 2025en
dc.subjectCSCLen
dc.titleNumber of Players, Zero: Using Multi-Agent Collaboration to Evaluate Unsolvable Collaborative Itemsen
dc.typeconferencePaper
dc.identifier.doi10.22318/cscl2025.325936
Appears in Collections:ISLS Annual Meeting 2025

Files in This Item:
File SizeFormat 
CSCL2025_409-414.pdf375.26 kBAdobe PDFView/Open


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