TeamFusion: Supporting Open-ended Team Decisions with Multi-Agent Systems

ACL ARR 2026 January Submission2415 Authors

Keywords: Team decision support, Open ended tasks, LLM agents, Human-AI interaction

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.

Paper Type: Long

Research Area: AI/LLM Agents

Research Area Keywords: human-AI interaction/cooperation, human-in-the-loop, LLM/AI agents, applications

Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models

Languages Studied: English

Submission Number: 2415