EcoAgent: An Efficient Device-Cloud Collaborative Multi-Agent Framework for Mobile Automation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yi, Biao, Hu, Xavier, Chen, Yurun, Zhang, Shengyu, Yang, Hongxia, Wu, Fan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912714360619008
author Yi, Biao
Hu, Xavier
Chen, Yurun
Zhang, Shengyu
Yang, Hongxia
Wu, Fan
author_facet Yi, Biao
Hu, Xavier
Chen, Yurun
Zhang, Shengyu
Yang, Hongxia
Wu, Fan
contents 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. Our project is available here: https://github.com/Yi-Biao/EcoAgent.
format Preprint
id arxiv_https___arxiv_org_abs_2505_05440
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EcoAgent: An Efficient Device-Cloud Collaborative Multi-Agent Framework for Mobile Automation
Yi, Biao
Hu, Xavier
Chen, Yurun
Zhang, Shengyu
Yang, Hongxia
Wu, Fan
Artificial Intelligence
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. Our project is available here: https://github.com/Yi-Biao/EcoAgent.
title EcoAgent: An Efficient Device-Cloud Collaborative Multi-Agent Framework for Mobile Automation
topic Artificial Intelligence
url https://arxiv.org/abs/2505.05440