CooT: Learning to Coordinate In-Context with Coordination Transformers

ICLR 2026 Conference Submission16717 Authors

Keywords: In-Context Learning, In-Context Reinforcement Learning, Multi-Agent Coordination, Human-AI Collaboration, Transformers for Decision Making

TL;DR: We present Coordination Transformers (CooT), an in-context learning framework that can efficiently and adaptively coordinate with unseen partners.

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 population-based approaches, gradient-based fine-tuning, and a Meta-RL-inspired contextual adaptation method. Notably, fine-tuning proves unstable and ineffective, while Meta-RL struggles to achieve reliable coordination. By contrast, CooT achieves stable, rapid in-context adaptation and is consistently ranked the most effective collaborator in human evaluations.

Primary Area: reinforcement learning

Submission Number: 16717