paper-with-me

Papers

OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments

2026-04-03 · Felix Henry, Xiaochen Lin, Jiangyou Zhu, Yangfan, Bingqian Zhang, Min Chen, Shiyu Huang arxiv

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 evaluate GUI agents in omni-modal smartphone environments. OmniGUI provides continuous, interleaved multimodal inputs comprising 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, their action prediction performance degrades significantly in environments requiring synchronous temporal and auditory signals. Furthermore, ablation studies isolate specific operational bottlenecks, notably cross-modal interference when 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.

📄 PDF Abstract BibTeX arXiv:2605.18758

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

OmniGuide: Universal Guidance Fields for Enhancing Generalist Robot Policies

2026-03-09 · Yunzhou Song, Long Le, Yong-Hyun Park, Jie Wang 외 arxiv

Vision-language-action(VLA) models have shown great promise as generalist policies for a large range of relatively simple tasks. However, they demonstrate limited performance on more complex tasks, such as those requirin…

OpenOmni: A Collaborative Open Source Tool for Building Future-Ready Multimodal Conversational Agents

2024-08-06 · Qiang Sun, Yuanyi Luo, Sirui Li, Wenxiao Zhang 외

Multimodal conversational agents are highly desirable because they offer natural and human-like interaction. However, there is a lack of comprehensive end-to-end solutions to support collaborative development and benchma…

BenchmarkingRetrieval-augmented GenerationSpeech-to-Text

Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents

2025-08-27 · Zhixin Lin, Jungang Li, Shidong Pan, Yibo Shi 외 arxiv

Smartphones bring significant convenience to users but also enable devices to extensively record various types of personal information. Existing smartphone agents powered by Multimodal Large Language Models (MLLMs) have …

OS-Themis: A Scalable Critic Framework for Generalist GUI Rewards

2026-03-19 · Zehao Li, Zhenyu Wu, Yibo Zhao, Bowen Yang 외 arxiv

Reinforcement Learning (RL) has the potential to improve the robustness of GUI agents in stochastic environments, yet training is highly sensitive to the quality of the reward function. Existing reward approaches struggl…

Reinforcement LearningDecision Making

OmniPlay: Benchmarking Omni-Modal Models on Omni-Modal Game Playing

2025-08-06 · Fuqing Bie, Shiyu Huang, Xijia Tao, Zhiqin Fang 외 arxiv

While generalist foundation models like Gemini and GPT-4o demonstrate impressive multi-modal competence, existing evaluations fail to test their intelligence in dynamic, interactive worlds. Static benchmarks lack agency,…