RoundTable: Investigating Group Decision-Making Mechanism in Multi-Agent Collaboration
This work addresses the problem of optimizing collaboration in multi-agent systems for researchers and practitioners, though it is incremental as it systematically studies existing mechanisms.
The paper investigated how different group decision-making mechanisms, such as voting rules, impact collaboration quality and efficiency in multi-agent systems, finding that majority voting leads to inefficiency and unanimous voting reduces initial performance by 87%, while language-based early stopping improved performance by 13% and reduced rounds by 50%.
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.