Coot: Learning To Coordinate In-context With Coordination Transformers

Abstract

Effective coordination among artificial agents in dynamic and uncertain environments remains a significant challenge in multi-agent systems. Existing approaches, such as self-play and population-based methods, either generalize poorly to unseen partners or require impractically extensive fine-tuning. To overcome these limitations, we propose Coordination Transformers (\coot), a novel in-context coordination framework that uses recent interaction histories to rapidly adapt to unseen partners. Unlike prior approaches that primarily aim to diversify training partners, \coot explicitly focuses on adapting to new partner behaviors by predicting actions aligned with observed interactions. Trained on trajectories collected from diverse pairs of agents with complementary preferences, \coot quickly learns effective coordination strategies without explicit supervision or parameter updates. Across diverse coordination tasks in Overcooked, \coot consistently outperforms baselines including populat

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywang2025coot

Related papers

• Learning To Coordinate With Anyone (2023)0.00
• Tackling Cooperative Incompatibility For Zero-shot Human-ai Coordination (2023)0.00
• Cooperative Open-ended Learning Framework For Zero-shot Coordination (2023)0.00
• Coach-player Multi-agent Reinforcement Learning For Dynamic Team Composition (2021)0.00
• "other-play" For Zero-shot Coordination (2020)0.00
• Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination (2025)0.00
• Enhancing Multi-agent Coordination Through Common Operating Picture Integration (2023)0.00
• Learning To Coordinate Under Threshold Rewards: A Cooperative Multi-agent Bandit Framework (2025)0.00