# UItron: Foundational GUI Agent with Advanced Perception and Planning

## TL;DR

UItron is a foundational GUI agent model that integrates advanced perception and planning, leveraging systemic data engineering and interactive infrastructure to improve performance in GUI tasks, especially in Chinese app scenarios.

## Contribution

The paper introduces UItron, a novel open-source GUI agent model with advanced perception, grounding, and planning capabilities, and demonstrates its effectiveness through comprehensive data strategies and interactive environments.

## Key findings

- UItron outperforms existing models in GUI perception, grounding, and planning benchmarks.
- It achieves significant progress in Chinese mobile app scenarios.
- The model demonstrates strong interaction proficiency with top-tier Chinese apps.

## Abstract

GUI agent aims to enable automated operations on Mobile/PC devices, which is an important task toward achieving artificial general intelligence. The rapid advancement of VLMs accelerates the development of GUI agents, owing to their powerful capabilities in visual understanding and task planning. However, building a GUI agent remains a challenging task due to the scarcity of operation trajectories, the availability of interactive infrastructure, and the limitation of initial capabilities in foundation models. In this work, we introduce UItron, an open-source foundational model for automatic GUI agents, featuring advanced GUI perception, grounding, and planning capabilities. UItron highlights the necessity of systemic data engineering and interactive infrastructure as foundational components for advancing GUI agent development. It not only systematically studies a series of data engineering strategies to enhance training effects, but also establishes an interactive environment connecting both Mobile and PC devices. In training, UItron adopts supervised finetuning over perception and planning tasks in various GUI scenarios, and then develop a curriculum reinforcement learning framework to enable complex reasoning and exploration for online environments. As a result, UItron achieves superior performance in benchmarks of GUI perception, grounding, and planning. In particular, UItron highlights the interaction proficiency with top-tier Chinese mobile APPs, as we identified a general lack of Chinese capabilities even in state-of-the-art solutions. To this end, we manually collect over one million steps of operation trajectories across the top 100 most popular apps, and build the offline and online agent evaluation environments. Experimental results demonstrate that UItron achieves significant progress in Chinese app scenarios, propelling GUI agents one step closer to real-world application.