Towards Zero-Shot Coordination between Teams of Agents: The N-XPlay Framework
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912443839545344 |
|---|---|
| author | Abderezaei, Ava Lin, Chi-Hui Miceli, Joseph Sivagnanadasan, Naren Aroca-Ouellette, Stéphane Brawer, Jake Roncone, Alessandro |
| author_facet | Abderezaei, Ava Lin, Chi-Hui Miceli, Joseph Sivagnanadasan, Naren Aroca-Ouellette, Stéphane Brawer, Jake Roncone, Alessandro |
| contents | Zero-shot coordination (ZSC) -- the ability to collaborate with unfamiliar partners -- is essential to making autonomous agents effective teammates. Existing ZSC methods evaluate coordination capabilities between two agents who have not previously interacted. However, these scenarios do not reflect the complexity of real-world multi-agent systems, where coordination often involves a hierarchy of sub-groups and interactions between teams of agents, known as Multi-Team Systems (MTS). To address this gap, we first introduce N-player Overcooked, an N-agent extension of the popular two-agent ZSC benchmark, enabling evaluation of ZSC in N-agent scenarios. We then propose N-XPlay for ZSC in N-agent, multi-team settings. Comparison against Self-Play across two-, three- and five-player Overcooked scenarios, where agents are split between an ``ego-team'' and a group of unseen collaborators shows that agents trained with N-XPlay are better able to simultaneously balance ``intra-team'' and ``inter-team'' coordination than agents trained with SP. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_17560 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Zero-Shot Coordination between Teams of Agents: The N-XPlay Framework Abderezaei, Ava Lin, Chi-Hui Miceli, Joseph Sivagnanadasan, Naren Aroca-Ouellette, Stéphane Brawer, Jake Roncone, Alessandro Multiagent Systems Artificial Intelligence Zero-shot coordination (ZSC) -- the ability to collaborate with unfamiliar partners -- is essential to making autonomous agents effective teammates. Existing ZSC methods evaluate coordination capabilities between two agents who have not previously interacted. However, these scenarios do not reflect the complexity of real-world multi-agent systems, where coordination often involves a hierarchy of sub-groups and interactions between teams of agents, known as Multi-Team Systems (MTS). To address this gap, we first introduce N-player Overcooked, an N-agent extension of the popular two-agent ZSC benchmark, enabling evaluation of ZSC in N-agent scenarios. We then propose N-XPlay for ZSC in N-agent, multi-team settings. Comparison against Self-Play across two-, three- and five-player Overcooked scenarios, where agents are split between an ``ego-team'' and a group of unseen collaborators shows that agents trained with N-XPlay are better able to simultaneously balance ``intra-team'' and ``inter-team'' coordination than agents trained with SP. |
| title | Towards Zero-Shot Coordination between Teams of Agents: The N-XPlay Framework |
| topic | Multiagent Systems Artificial Intelligence |
| url | https://arxiv.org/abs/2506.17560 |