TeamFusion: Supporting Open-ended Teamwork with Multi-Agent Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Jiale, Bursztyn, Victor S., Ai, Lin, Wang, Haoliang, Choudhary, Sunav, Mitra, Saayan, Wu, Qingyun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910153977102336
author Liu, Jiale
Bursztyn, Victor S.
Ai, Lin
Wang, Haoliang
Choudhary, Sunav
Mitra, Saayan
Wu, Qingyun
author_facet Liu, Jiale
Bursztyn, Victor S.
Ai, Lin
Wang, Haoliang
Choudhary, Sunav
Mitra, Saayan
Wu, Qingyun
contents In open-ended domains, teams must reconcile diverse viewpoints to produce strong deliverables. Answer aggregation approaches commonly used in closed domains are ill-suited to this setting, as they tend to suppress minority perspectives rather than resolve underlying disagreements. We present TeamFusion, a multi-agent system designed to support teamwork in open-ended domains by: 1. Instantiating a proxy agent for each team member conditioned on their expressed preferences; 2. Conducting a structured discussion to surface agreements and disagreements; and 3. Synthesizing more consensus-oriented deliverables that feed into new iterations of discussion and refinement. We evaluate TeamFusion on two teamwork tasks where team members can assess how well their individual views are represented in team decisions and how consensually strong the final deliverables are, finding that it outperforms direct aggregation baselines across metrics, tasks, and team configurations.
format Preprint
id arxiv_https___arxiv_org_abs_2604_19589
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TeamFusion: Supporting Open-ended Teamwork with Multi-Agent Systems
Liu, Jiale
Bursztyn, Victor S.
Ai, Lin
Wang, Haoliang
Choudhary, Sunav
Mitra, Saayan
Wu, Qingyun
Multiagent Systems
In open-ended domains, teams must reconcile diverse viewpoints to produce strong deliverables. Answer aggregation approaches commonly used in closed domains are ill-suited to this setting, as they tend to suppress minority perspectives rather than resolve underlying disagreements. We present TeamFusion, a multi-agent system designed to support teamwork in open-ended domains by: 1. Instantiating a proxy agent for each team member conditioned on their expressed preferences; 2. Conducting a structured discussion to surface agreements and disagreements; and 3. Synthesizing more consensus-oriented deliverables that feed into new iterations of discussion and refinement. We evaluate TeamFusion on two teamwork tasks where team members can assess how well their individual views are represented in team decisions and how consensually strong the final deliverables are, finding that it outperforms direct aggregation baselines across metrics, tasks, and team configurations.
title TeamFusion: Supporting Open-ended Teamwork with Multi-Agent Systems
topic Multiagent Systems
url https://arxiv.org/abs/2604.19589