UI-Venus-2 Technical Report

  • 类型:arxiv
  • 标识:2609.00028
  • 链接:https://arxiv.org/abs/2609.00028
  • 主分类:agent
  • 形态:benchmark
  • TLDR: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) Environment
  • 待LLM分类:否
  • 来源文件
  • /inbox/tom/_candidates/2026-09-02-agent-rag-longcontext-candidates.json