Automating GUI tasks remains challenging due to reliance on textual representations, platform-specific action spaces, and limited reasoning capabilities. We introduce Aguvis, a unified vision-based framework for autonomous GUI agents that directly operates on screen images, standardizes cross-platform interactions and incorporates structured reasoning via inner monologue. To enable this, we construct Aguvis Data Collection, a large-scale dataset with multimodal grounding and reasoning annotations, and develop a two-stage training pipeline that separates GUI grounding from planning and reasoning. Experiments show that Aguvis achieves state-of-the-art performance across offline and real-world online benchmarks, marking the first fully autonomous vision-based GUI agent that operates without closed-source models. We open-source all datasets, models, and training recipes at https://aguvis-project.github.io to advance future research.
@article{arxiv.2412.04454,
title = {Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction},
author = {Yiheng Xu and Zekun Wang and Junli Wang and Dunjie Lu and Tianbao Xie and Amrita Saha and Doyen Sahoo and Tao Yu and Caiming Xiong},
journal= {arXiv preprint arXiv:2412.04454},
year = {2025}
}