OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Execution

TL;DR

OmegaUse is a versatile GUI agent model that autonomously executes tasks across mobile and desktop platforms, utilizing high-quality data, innovative training, and a Mixture-of-Experts backbone, achieving state-of-the-art performance on multiple benchmarks.

Contribution

The paper introduces OmegaUse, a novel general-purpose GUI agent with a new data synthesis framework, a two-stage training paradigm, and a Mixture-of-Experts architecture for improved autonomous task execution.

Findings

Achieves 96.3% on ScreenSpot-V2 benchmark.

Reaches 79.1% step success on AndroidControl.

Attains 74.24% step success on ChiM-Nav.

Abstract

Graphical User Interface (GUI) agents show great potential for enabling foundation models to complete real-world tasks, revolutionizing human-computer interaction and improving human productivity. In this report, we present OmegaUse, a general-purpose GUI agent model for autonomous task execution on both mobile and desktop platforms, supporting computer-use and phone-use scenarios. Building an effective GUI agent model relies on two factors: (1) high-quality data and (2) effective training methods. To address these, we introduce a carefully engineered data-construction pipeline and a decoupled training paradigm. For data construction, we leverage rigorously curated open-source datasets and introduce a novel automated synthesis framework that integrates bottom-up autonomous exploration with top-down taxonomy-guided generation to create high-fidelity synthetic data. For training, to better leverage these data, we adopt a two-stage strategy: Supervised Fine-Tuning (SFT) to establish fundamental interaction syntax, followed by Group Relative Policy Optimization (GRPO) to improve spatial grounding and sequential planning. To balance computational efficiency with agentic reasoning capacity, OmegaUse is built on a Mixture-of-Experts (MoE) backbone. To evaluate cross-terminal capabilities in an offline setting, we introduce OS-Nav, a benchmark suite spanning multiple operating systems: ChiM-Nav, targeting Chinese Android mobile environments, and Ubu-Nav, focusing on routine desktop interactions on Ubuntu. Extensive experiments show that OmegaUse is highly competitive across established GUI benchmarks, achieving a state-of-the-art (SOTA) score of 96.3% on ScreenSpot-V2 and a leading 79.1% step success rate on AndroidControl. OmegaUse also performs strongly on OS-Nav, reaching 74.24% step success on ChiM-Nav and 55.9% average success on Ubu-Nav.