{"slug": "ui-venus-2-technical-report", "title": "UI-Venus-2 Technical Report", "summary": "Researchers released UI-Venus-2, a general-purpose foundation GUI agent that operates across mobile, web, and desktop environments through a unified closed-loop reasoning-action framework, expanding coverage to more than 170 multilingual mobile apps and native desktop operating systems. The agent employs trace-level and sample-level evaluators with visual keypoints and multi-model voting for reliable reinforcement learning signals, and integrates safety-aware mechanisms for controlled execution of consequential actions. The open-source release aims to advance generalizable, verifiable, and self-reflective agents for real-world applications.", "body_md": "arXiv:2609.00028v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/ui-venus-2-technical-report", "canonical_source": "https://arxiv.org/abs/2609.00028", "published_at": "2026-09-02 04:00:00+00:00", "updated_at": "2026-09-02 04:26:31.148784+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-research", "ai-products"], "entities": ["UI-Venus-2", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/ui-venus-2-technical-report", "markdown": "https://wpnews.pro/news/ui-venus-2-technical-report.md", "text": "https://wpnews.pro/news/ui-venus-2-technical-report.txt", "jsonld": "https://wpnews.pro/news/ui-venus-2-technical-report.jsonld"}}