mlsanityData to 14 Oct 2026

Towards Zero-Shot Coordination between Teams of Agents: The N-XPlay Framework

arXiv 2506.17560 ↗First posted 21 Jun 2025cs.MA cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 7 of its 12 references that are in the map. First posted on arXiv 21 Jun 2025.

Builds on

7 of 12 references.

References · 7

  1. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 349
  2. 2021Collaborating with Humans without Human Datacited by 142
  3. 2021Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordinationcited by 70
  4. 2023PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordinationcited by 25
  5. 2024Learning to Cooperate with Humans using Generative Agentscited by 24
  6. 2025Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractionscited by 2
  7. 2024ROMA-iQSS: An Objective Alignment Approach via State-Based Value Learning and ROund-Robin Multi-Agent Schedulingcited by 1

Built on by

Not cited yet.