@inproceedings{liu-etal-2026-teamfusion,
    title = "{T}eam{F}usion: Supporting Open-ended Teamwork with Multi-Agent Systems",
    author = "Liu, Jiale  and
      Bursztyn, Victor  and
      Ai, Lin  and
      Wang, Haoliang  and
      Choudhary, Sunav  and
      Mitra, Saayan  and
      Wu, Qingyun",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.657/",
    pages = "14435--14456",
    ISBN = "979-8-89176-390-6",
    abstract = "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 elicit agreements and disagreements; and 3. Synthesizing more consensus-oriented deliverables that feed into new iterations of discussion and synthesis. We evaluate TeamFusion on two teamwork tasks where team members can judge how well their individual views are represented in team decisions and how consensually good the final deliverables are, finding that it outperforms direct aggregation baselines across metrics, tasks, and team configurations."
}