GUICourse: From General Vision Language Models to Versatile GUI Agents

TL;DR

This paper introduces GUICourse, a comprehensive dataset suite designed to enhance general Vision Language Models for versatile GUI navigation tasks, improving their OCR, grounding, and interaction capabilities.

Contribution

We develop GUICourse, including datasets GUIEnv, GUIAct, and GUIChat, to train and improve VLMs for practical GUI agent applications, addressing current limitations.

Findings

GUI agents outperform baseline VLMs on GUI tasks

Small GUI agents (3.1B parameters) perform well on complex tasks

Ablation studies reveal key training factors for GUI agent performance

Abstract

Utilizing Graphic User Interface (GUI) for human-computer interaction is essential for accessing a wide range of digital tools. Recent advancements in Vision Language Models (VLMs) highlight the compelling potential to develop versatile agents to help humans finish GUI navigation tasks. However, current VLMs are challenged in terms of fundamental abilities (OCR and grounding) and GUI knowledge (the functions and control methods of GUI elements), preventing them from becoming practical GUI agents. To solve these challenges, we contribute GUICourse, a suite of datasets to train visual-based GUI agents from general VLMs. First, we introduce the GUIEnv dataset to strengthen the OCR and grounding capabilities of VLMs. Then, we introduce the GUIAct and GUIChat datasets to enrich their knowledge of GUI components and interactions. Experiments demonstrate that our GUI agents have better performance on common GUI tasks than their baseline VLMs. Even the small-size GUI agent (with 3.1B parameters) can still work well on single-step and multi-step GUI tasks. Finally, we analyze the different varieties in the training stage of this agent by ablation study. Our source codes and datasets are released at https://github.com/yiye3/GUICourse.