Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Towards Zero-Shot Coordination between Teams of Agents: The N-XPlay Framework (2506.17560v1)

Published 21 Jun 2025 in cs.MA and cs.AI

Abstract: 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 balanceintra-team'' and ``inter-team'' coordination than agents trained with SP.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (7)
  1. Ava Abderezaei (3 papers)
  2. Chi-Hui Lin (3 papers)
  3. Joseph Miceli (1 paper)
  4. Naren Sivagnanadasan (2 papers)
  5. Stéphane Aroca-Ouellette (22 papers)
  6. Jake Brawer (4 papers)
  7. Alessandro Roncone (33 papers)