English

RoundTable: Investigating Group Decision-Making Mechanism in Multi-Agent Collaboration

Multiagent Systems 2025-06-05 v2 Artificial Intelligence

Abstract

Effective group decision-making is critical in Multi-Agent Systems (MAS). Yet, how different mechanisms for reaching consensus impact collaboration quality and efficiency remains understudied. We conduct a systematic study on group decision-making mechanisms in a decentralized setting. Through controlled experiments, we analyze how different voting rules affect decision quality and efficiency in a multi-round collaboration. Results reveal that majority voting often cause inefficient collaboration due to its strict acceptance criteria. At the extreme, unanimous voting gives 87% lower initial performance than the best-performing method. Our qualitative analysis of cross-agent communication shows that messages become longer and more repetitive over time: while message length increases by 84%, similarity to the previous round increases to 90%. Based on these insights, language-based early stopping methods make the performance 13% closer to oracle while reducing rounds by 50%. Our findings highlight the crucial role of group decision-making in optimizing MAS collaboration.

Keywords

Cite

@article{arxiv.2411.07161,
  title  = {RoundTable: Investigating Group Decision-Making Mechanism in Multi-Agent Collaboration},
  author = {Young-Min Cho and Raphael Shu and Nilaksh Das and Tamer Alkhouli and Yi-An Lai and Jason Cai and Monica Sunkara and Yi Zhang and Dan Roth},
  journal= {arXiv preprint arXiv:2411.07161},
  year   = {2025}
}

Comments

preprint

R2 v1 2026-06-28T19:55:49.285Z