Multi-agent In-context Coordination via Decentralized Memory Retrieval
Tao Jiang, Zichuan Lin, Lihe Li, Yi-Chen Li, Cong Guan, Lei Yuan, Zongzhang Zhang, Yang Yu
Abstract
Large transformer models, trained on diverse datasets, have demonstrated impressive few-shot performance on previously unseen tasks without requiring parameter updates. This capability has also been explored in Reinforcement Learning (RL), where agents interact with the environment to retrieve context and maximize cumulative rewards, showcasing strong adaptability in complex settings. However, in cooperative Multi-Agent Reinforcement Learning (MARL), where agents must coordinate toward a shared goal, decentralized policy deployment can lead to mismatches in task alignment and reward assignment, limiting the efficiency of policy adaptation. To address this challenge, we introduce Multi-agent In-context Coordination via Decentralized Memory Retrieval (MAICC), a novel approach designed to enhance coordination by fast adaptation. Our method involves training a centralized embedding model to capture fine-grained trajectory representations, followed by decentralized models that approximate the centralized one to obtain team-level task information. Based on the learned embeddings, relevant trajectories are retrieved as context, which, combined with the agents
BibTeX
@inproceedings{aaai2026_multiagentincont,
title = {Multi-agent In-context Coordination via Decentralized Memory Retrieval},
author = {Tao Jiang and Zichuan Lin and Lihe Li and Yi-Chen Li and Cong Guan and Lei Yuan and Zongzhang Zhang and Yang Yu and Deheng Ye},
booktitle = {AAAI 2026},
year = {2026}
}