UI-Venus-2 Technical Report

Hugging Face Daily Papers Papers

Summary

UI-Venus-2 is an open-source multimodal GUI agent designed for digital automation across mobile, web, and desktop environments, using unified reasoning-action loops and robust verification to enable reliable real-world applications.

Multimodal GUI agents have emerged as a promising paradigm for digital task automation, yet transitioning from benchmark-oriented models to dependable real-world applications remains challenging due to limited environment coverage, brittle task construction, and unreliable reward verification. In this work, we present UI-Venus-2, a general-purpose foundation GUI agent designed to operate across mobile, web, and desktop environments through a unified closed-loop reasoning-action framework. To bridge the gap toward practical deployment, we jointly scale three critical dimensions: (1) Environments, expanding coverage to more than 170 multilingual mobile apps and native desktop operating systems; (2) Tasks, employing a deep-research pipeline for function-grounded instruction generation; and (3) Verification, adopting trace-level and sample-level evaluators with visual keypoints and multi-model voting to ensure reliable RL signals for training. Furthermore, we integrate safety-aware mechanisms to ensure controlled execution of consequential actions. By offering a capable, efficient, and open-source foundation, UI-Venus-2 advances the field toward more generalizable, verifiable, and self-reflective agents for real-world applications.
Original Article
View Cached Full Text

Cached at: 09/02/26, 03:44 AM

Paper page - UI-Venus-2 Technical Report

Source: https://huggingface.co/papers/2609.00028 Published on Aug 27

#2 Paper of the day Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

UI-Venus-2 is a general-purpose multimodal GUI agent that uses unified reasoning-action loops, expanded environment coverage, and robust verification to enable reliable real-world digital automation.

Multimodal GUI agentshave emerged as a promising paradigm for digital task automation, yet transitioning from benchmark-oriented models to dependable real-world applications remains challenging due to limited environment coverage, brittle task construction, and unreliable reward verification. In this work, we present UI-Venus-2, a general-purpose foundation GUI agent designed to operate across mobile, web, and desktop environments through a unifiedclosed-loop reasoning-action framework. To bridge the gap toward practical deployment, we jointly scale three critical dimensions: (1) Environments, expanding coverage to more than 170 multilingual mobile apps and native desktop operating systems; (2) Tasks, employing a deep-research pipeline forfunction-grounded instruction generation; and (3) Verification, adopting trace-level andsample-level evaluatorswithvisual keypointsandmulti-model votingto ensure reliableRL signalsfor training. Furthermore, we integratesafety-aware mechanismsto ensure controlled execution of consequential actions. By offering a capable, efficient, and open-source foundation, UI-Venus-2 advances the field toward more generalizable, verifiable, and self-reflective agents for real-world applications.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2609\.00028

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

Models citing this paper1

#### inclusionAI/UI-Venus-2-9B Image-Text-to-Text• 1.47M• Updated25 minutes ago • 2.07k • 20

Datasets citing this paper1

#### inclusionAI/VenusBench-CAPTCHA Viewer• Updated19 minutes ago • 219 • 2

Spaces citing this paper1

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

Papers with Code Trending

UI-TARS-2 is a native GUI-centered agent model that addresses data scalability, multi-turn RL, and environment stability challenges, achieving state-of-the-art results on GUI benchmarks (88.2 on Online-Mind2Web, 47.5 on OSWorld, 50.6 on WindowsAgentArena,73.3 on AndroidWorld) and outperforming Claude and OpenAI agents.

MAI-UI Technical Report: Real-World Centric Foundation GUI Agents

Papers with Code Trending

The MAI-UI technical report presents a family of foundation GUI agents in multiple sizes, addressing real-world deployment challenges with a self-evolving data pipeline, device-cloud collaboration, and online RL, achieving state-of-the-art results on GUI grounding and mobile navigation benchmarks.

Xiaomi-GUI-0 Technical Report

Hugging Face Daily Papers

This technical report presents Xiaomi-GUI-0, a native multimodal GUI agent trained and evaluated in real-device environments using a hybrid infrastructure and a progressive training pipeline, achieving high success rates and improved stability on real-world mobile tasks.