CooT: Learning to Coordinate In-Context with Coordination Transformers

Effective coordination among unfamiliar partners remains a major challenge in multi-agent systems. Existing approaches, such as populationbased methods, improve robustness through diversity but often lack mechanisms for efficient adaptation beyond training distribution. Moreover, fine-tuning is impractical in few-shot settings due to its high interaction cost. To address these limitations, we propose Coordination Transformer (COOT ), a framework that leverages in-context learning (ICL) for real-time partner adaptation. Unlike prior ICL approaches that focus on task generalization, COOT is designed to generalize across diverse partner behaviors. Trained on trajectories from behaviorpreferring agents, it learns to align actions with partner intentions purely through observation. We evaluate COOT on two challenging multi-agent benchmarks: Overcooked and Google Research Football. Results show that COOT consistently outperforms population-based methods, gradientbased fine-tuning, and Meta-RL baselines, achieving stable and rapid adaptation without parameter updates. Human evaluations also identify COOT as a preferred collaborator, and our ablations confirm its ability to adapt quickly to new partners and remain stable under sudden partner changes, making it reliable for real-world human-AI collaboration. Demos are available at https: //coot-project.github.io/coot/ .