The Year in AI Papers
The year/Independent research

Paper 2602.09082

UI-Venus-1.5 Technical Report

Venus Team, Changlong Gao, Zhangxuan Gu, Yulin Liu, Xinyu Qiu, Shuheng Shen, Yue Wen, Tianyu Xia, Zhenyu Xu, Zhengwen Zeng, Beitong Zhou, Xingran Zhou, et al.

Published
Feb 2026
Research lab
Independent
Citations
27
GitHub
1K stars

01 In brief

Summary

UI-Venus-1.5 is a unified, end-to-end GUI agent family (2B, 8B, and 30B-A3B variants) built on Qwen3-VL, designed for robust real-world applications.

It introduces three key advances over UI-Venus-1.0: a Mid-Training stage using 10B tokens from 30+ datasets to establish foundational GUI semantics; Online Reinforcement Learning with full-trajectory rollouts to align training with long-horizon navigation; and a single unified model via Model Merging (TIES-Merge) of domain-specific grounding, web, and mobile models.

The model achieves state-of-the-art results on ScreenSpot-Pro (69.6%), VenusBench-GD (75.0%), AndroidWorld (77.6%), and other benchmarks, outperforming strong baselines like MAI-UI-32B and Holo2.

It also demonstrates robust navigation across 40+ Chinese mobile apps.

The training pipeline includes Mid-Training, Offline-RL, Online-RL, and Model Merge, with ablations showing each stage contributes to performance.

The model is optimized for practical utility, handling tasks like ticket booking and shopping in real-world scenarios.

02 From the paper

Abstract

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