arxiv:2602.16855

Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents

Published on Feb 15

· Submitted by

xuhaiyang on Feb 20

#2 Paper of the day

TongyiLab

Upvote

Authors:

Shengjie Zhou ,

Xuhao Hu ,

Junjie Cao ,

Junyang Lin ,

Abstract

GUI-Owl-1.5 is a multi-platform GUI agent model with multiple sizes that achieves state-of-the-art performance on GUI automation, grounding, tool-calling, and memory tasks through innovations in hybrid data pipelines, unified reasoning enhancement, and multi-platform reinforcement learning.

AI-generated summary

The paper introduces GUI-Owl-1.5, the latest native GUI agent model that features instruct/thinking variants in multiple sizes (2B/4B/8B/32B/235B) and supports a range of platforms (desktop, mobile, browser, and more) to enable cloud-edge collaboration and real-time interaction. GUI-Owl-1.5 achieves state-of-the-art results on more than 20+ GUI benchmarks on open-source models: (1) on GUI automation tasks, it obtains 56.5 on OSWorld, 71.6 on AndroidWorld, and 48.4 on WebArena; (2) on grounding tasks, it obtains 80.3 on ScreenSpotPro; (3) on tool-calling tasks, it obtains 47.6 on OSWorld-MCP, and 46.8 on MobileWorld; (4) on memory and knowledge tasks, it obtains 75.5 on GUI-Knowledge Bench. GUI-Owl-1.5 incorporates several key innovations: (1) Hybird Data Flywheel: we construct the data pipeline for UI understanding and trajectory generation based on a combination of simulated environments and cloud-based sandbox environments, in order to improve the efficiency and quality of data collection. (2) Unified Enhancement of Agent Capabilities: we use a unified thought-synthesis pipeline to enhance the model's reasoning capabilities, while placing particular emphasis on improving key agent abilities, including Tool/MCP use, memory and multi-agent adaptation; (3) Multi-platform Environment RL Scaling: We propose a new environment RL algorithm, MRPO, to address the challenges of multi-platform conflicts and the low training efficiency of long-horizon tasks. The GUI-Owl-1.5 models are open-sourced, and an online cloud-sandbox demo is available at https://github.com/X-PLUG/MobileAgent.

View arXiv page View PDF Project page Add to collection

Community

xhyandwyy

Paper submitter 1 day ago

The paper introduces GUI-Owl-1.5, the latest native GUI agent model that features instruct/thinking variants in multiple sizes (2B/4B/8B/32B/235B) and supports a range of platforms (desktop, mobile, browser, and more) to enable cloud-edge collaboration and real-time interaction. GUI-Owl-1.5 achieves state-of-the-art results on more than 20+ GUI benchmarks on open-source models: (1) on GUI automation tasks, it obtains 56.5 on OSWorld, 71.6 on AndroidWorld, and 48.4 on WebArena; (2) on grounding tasks, it obtains 80.3 on ScreenSpotPro; (3) on tool-calling tasks, it obtains 47.6 on OSWorld-MCP, and 46.8 on MobileWorld; (4) on memory and knowledge tasks, it obtains 75.5 on GUI-Knowledge Bench. GUI-Owl-1.5 incorporates several key innovations: (1) \textbf{Hybird Data Flywheel}: we construct the data pipeline for UI understanding and trajectory generation based on a combination of simulated environments and cloud-based sandbox environments, in order to improve the efficiency and quality of data collection. (2) \textbf{Unified Enhancement of Agent Capabilities}: we use a unified thought-synthesis pipeline to enhance the model's reasoning capabilities, while placing particular emphasis on improving key agent abilities, including Tool/MCP use, memory and multi-agent adaptation; (3) \textbf{Multi-platform Environment RL Scaling}: We propose a new environment RL algorithm, MRPO, to address the challenges of multi-platform conflicts and the low training efficiency of long-horizon tasks. The GUI-Owl-1.5 models are open-sourced, and an online cloud-sandbox demo is available at https://github.com/X-PLUG/MobileAgent.