Saved in:
Bibliographic Details
Main Authors: Wu, Zhen, Shi, Jiaxin, Murray, R. Charles, Rosé, Carolyn, Andres, Micah San
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.18877
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915569261871104
author Wu, Zhen
Shi, Jiaxin
Murray, R. Charles
Rosé, Carolyn
Andres, Micah San
author_facet Wu, Zhen
Shi, Jiaxin
Murray, R. Charles
Rosé, Carolyn
Andres, Micah San
contents For nearly two decades, conversational agents have played a critical role in structuring interactions in collaborative learning, shaping group dynamics, and supporting student engagement. The recent integration of large language models (LLMs) into these agents offers new possibilities for fostering critical thinking and collaborative problem solving. In this work, we begin with an open source collaboration support architecture called Bazaar and integrate an LLM-agent shell that enables introduction of LLM-empowered, real time, context sensitive collaborative support for group learning. This design and infrastructure paves the way for exploring how tailored LLM-empowered environments can reshape collaborative learning outcomes and interaction patterns.
format Preprint
id arxiv_https___arxiv_org_abs_2510_18877
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM Bazaar: A Service Design for Supporting Collaborative Learning with an LLM-Powered Multi-Party Collaboration Infrastructure
Wu, Zhen
Shi, Jiaxin
Murray, R. Charles
Rosé, Carolyn
Andres, Micah San
Human-Computer Interaction
Artificial Intelligence
For nearly two decades, conversational agents have played a critical role in structuring interactions in collaborative learning, shaping group dynamics, and supporting student engagement. The recent integration of large language models (LLMs) into these agents offers new possibilities for fostering critical thinking and collaborative problem solving. In this work, we begin with an open source collaboration support architecture called Bazaar and integrate an LLM-agent shell that enables introduction of LLM-empowered, real time, context sensitive collaborative support for group learning. This design and infrastructure paves the way for exploring how tailored LLM-empowered environments can reshape collaborative learning outcomes and interaction patterns.
title LLM Bazaar: A Service Design for Supporting Collaborative Learning with an LLM-Powered Multi-Party Collaboration Infrastructure
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2510.18877