UI-Venus-1.5打造统一GUI智能体，支持跨平台精准操作。
UI-Venus-1.5 Technical Report
- 通过模型融合整合多领域能力，构建单一统一智能体。
- 在ScreenSpot-Pro等三大赛事中刷新69.6%~77.6%准确率纪录。
- 适配中文移动端应用，真实场景下执行指令稳定可靠。
GUI智能体已成为自动化数字环境交互的有力范式，但实现广泛通用性与持续高性能仍具挑战。本文介绍统一端到端的GUI智能体UI-Venus-1.5，包含2B、8B两个密集型版本及30B-A3B混合专家版本，以适应不同下游场景。相比前代，新版本引入三大技术突破：(1) 利用30余数据集共100亿token进行中段训练，建立基础GUI语义；(2) 采用全轨迹在线强化学习，对齐长时程动态导航目标；(3) 通过模型融合，将领域专用模型（视觉定位、网页、移动端）合并为单一检查点。大量评估显示，该模型在ScreenSpot-Pro（69.6%）、VenusBench-GD（75.0%）、AndroidWorld（77.6%）等基准上达到新SOTA水平，显著超越既有强基线。此外，其在多种中文移动应用中展现出鲁棒导航能力，可有效执行真实用户指令。代码：https://github.com/inclusionAI/UI-Venus；模型：https://huggingface.co/collections/inclusionAI/ui-venus
原文摘要 · Abstract (English)
GUI agents have emerged as a powerful paradigm for automating interactions in digital environments, yet achieving both broad generality and consistently strong task performance remains challenging. In this report, we present UI-Venus-1.5, a unified, end-to-end GUI Agent designed for robust real-world applications. The proposed model family comprises two dense variants (2B and 8B) and one mixture-of-experts variant (30B-A3B) to meet various downstream application scenarios. Compared to our previous version, UI-Venus-1.5 introduces three key technical advances: (1) a comprehensive Mid-Training stage leveraging 10 billion tokens across 30+ datasets to establish foundational GUI semantics; (2) Online Reinforcement Learning with full-trajectory rollouts, aligning training objectives with long-horizon, dynamic navigation in large-scale environments; and (3) a single unified GUI Agent constructed via Model Merging, which synthesizes domain-specific models (grounding, web, and mobile) into one cohesive checkpoint. Extensive evaluations demonstrate that UI-Venus-1.5 establishes new state-of-the-art performance on benchmarks such as ScreenSpot-Pro (69.6%), VenusBench-GD (75.0%), and AndroidWorld (77.6%), significantly outperforming previous strong baselines. In addition, UI-Venus-1.5 demonstrates robust navigation capabilities across a variety of Chinese mobile apps, effectively executing user instructions in real-world scenarios. Code: https://github.com/inclusionAI/UI-Venus; Model: https://huggingface.co/collections/inclusionAI/ui-venus
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。