CooT: Learning to Coordinate In-Context with Coordination Transformers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Huai-Chih, Chuang, Hsiang-Chun, Cheng, Hsi-Chun, Wu, Dai-Jie, Sun, Shao-Hua
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911693299253248
author Wang, Huai-Chih
Chuang, Hsiang-Chun
Cheng, Hsi-Chun
Wu, Dai-Jie
Sun, Shao-Hua
author_facet Wang, Huai-Chih
Chuang, Hsiang-Chun
Cheng, Hsi-Chun
Wu, Dai-Jie
Sun, Shao-Hua
contents Effective coordination among unfamiliar partners remains a major challenge in multi-agent systems. Existing approaches, such as population-based 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 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 behavior-preferring 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, gradient-based 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_23549
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CooT: Learning to Coordinate In-Context with Coordination Transformers
Wang, Huai-Chih
Chuang, Hsiang-Chun
Cheng, Hsi-Chun
Wu, Dai-Jie
Sun, Shao-Hua
Artificial Intelligence
Human-Computer Interaction
Machine Learning
Effective coordination among unfamiliar partners remains a major challenge in multi-agent systems. Existing approaches, such as population-based 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 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 behavior-preferring 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, gradient-based 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.
title CooT: Learning to Coordinate In-Context with Coordination Transformers
topic Artificial Intelligence
Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2506.23549