EcoAgent: An Efficient Device-Cloud Collaborative Multi-Agent Framework for Mobile Automation
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (35) · 29838-29846
DOI: 10.1609/aaai.v40i35.40230 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Biao Yi und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
To tackle increasingly complex tasks, recent research on mobile agents has shifted towards multi-agent collaboration. Current mobile multi-agent systems are primarily deployed in the cloud, leading to high latency and operational costs. A straightforward idea is to deploy a device–cloud collaborative multi-agent system, which is nontrivial, as directly extending existing systems introduces new challenges: (1) reliance on cloud-side verification requires uploading mobile screenshots, compromising user privacy; and (2) open-loop cooperation lacking device-to-cloud feedback, underutilizing device resources and increasing latency. To overcome these limitations, we propose EcoAgent, a closed-loop device-cloud collaborative multi-agent framework designed for privacy-aware, efficient, and responsive mobile automation. EcoAgent integrates a novel reasoning approach, Dual-ReACT, into the cloud-based Planning Agent, fully exploiting cloud reasoning to compensate for limited on-device capacity, thereby enabling device-side verification and lightweight feedback. Furthermore, the device-based Observation Agent leverages a Pre-understanding Module to summarize screen content into concise textual descriptions, significantly reducing token usage and device-cloud communication overhead while preserving privacy. Experiments on AndroidWorld demonstrate that EcoAgent matches the task success rates of fully cloud-based agents, while reducing resource consumption and response latency.
Zitieren
APA
Yi, B., Hu, X., Chen, Y., Zhang, S., Yang, H., & Wu, F. (2026). EcoAgent: An Efficient Device-Cloud Collaborative Multi-Agent Framework for Mobile Automation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(35), 29838-29846. https://doi.org/10.1609/aaai.v40i35.40230
Vancouver
Yi B, Hu X, Chen Y, Zhang S, Yang H, Wu F. EcoAgent: An Efficient Device-Cloud Collaborative Multi-Agent Framework for Mobile Automation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(35):29838-29846. doi:10.1609/aaai.v40i35.40230
BibTeX
@article{Yi2026,
author = {Yi, Biao and Hu, Xueyu and Chen, Yurun and Zhang, Shengyu and Yang, Hongxia and Wu, Fan},
title = {EcoAgent: An Efficient Device-Cloud Collaborative Multi-Agent Framework for Mobile Automation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {35},
pages = {29838--29846},
doi = {10.1609/aaai.v40i35.40230}
}
EUVIMED