Paper page - OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments

Source: https://huggingface.co/papers/2605.18758

Abstract

OmniGUI presents a novel multimodal benchmark for GUI agents that incorporates simultaneous audio, video, and image inputs to better simulate real smartphone interactions.

Current benchmarks for graphical user interface (GUI) agents predominantly rely on static screenshots. However, real-world smartphone interaction routinely requires agents to process transient audio cues and temporal video dynamics that are tightly coupled with the moment of action. To bridge this gap, we introduce OmniGUI, the first step-level benchmark designed to evaluateGUI agentsin omni-modalsmartphone environments. OmniGUI provides continuous, interleavedmultimodal inputscomprising static images, synchronous audio, and video clips at every action step. The dataset encompasses 709 expert-demonstrated episodes (2,579 action steps) across 29 applications, systematically annotated with objective multimodal dependency levels. Because dedicated omni-modal GUI agent frameworks are currently in their nascent stage, we select foundational omni-modal models capable of natively processing interleaved inputs to serve as agent proxies for our initial baselines. Our empirical evaluation reveals that while current models exhibit competency on visually static tasks, theiraction predictionperformance degrades significantly in environments requiring synchronous temporal and auditory signals. Furthermore, ablation studies isolate specific operational bottlenecks, notablycross-modal interferencewhen processing task-irrelevant environmental noise. The complete dataset, evaluation pipeline, and baseline prompts are provided in the supplementary material. Project page: https://omni-gui.github.io.

View arXiv pageView PDFProject pageGitHub2Add to collection

Get this paper in your agent:

hf papers read 2605\.18758

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.18758 in a model README.md to link it from this page.

Datasets citing this paper1

#### OmniGUI/OmniGUI Viewer• Updated31 minutes ago • 2.61k • 6.21k • 2

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.18758 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.