RoundTable: Investigating Group Decision-Making Mechanism in Multi-Agent Collaboration
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912412246999040 |
|---|---|
| author | Cho, Young-Min Shu, Raphael Das, Nilaksh Alkhouli, Tamer Lai, Yi-An Cai, Jason Sunkara, Monica Zhang, Yi Roth, Dan |
| author_facet | Cho, Young-Min Shu, Raphael Das, Nilaksh Alkhouli, Tamer Lai, Yi-An Cai, Jason Sunkara, Monica Zhang, Yi Roth, Dan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_07161 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RoundTable: Investigating Group Decision-Making Mechanism in Multi-Agent Collaboration Cho, Young-Min Shu, Raphael Das, Nilaksh Alkhouli, Tamer Lai, Yi-An Cai, Jason Sunkara, Monica Zhang, Yi Roth, Dan Multiagent Systems Artificial Intelligence 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. |
| title | RoundTable: Investigating Group Decision-Making Mechanism in Multi-Agent Collaboration |
| topic | Multiagent Systems Artificial Intelligence |
| url | https://arxiv.org/abs/2411.07161 |