AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

UIPro: Unleashing Superior Interaction Capability For GUI Agents

Hongxin Li, Jingran Su, Jingfan Chen, Zheng Ju, Yuntao Chen, Qing Li, Zhaoxiang Zhang

ICCV 2025 · Multi-agent systems and games › LLM agents · approach: GUI agent memory and trajectories · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add denoising of GUI understanding data (ablation)UIPro-SLiME · FuncPredgrounding accuracy: 64.3 -> 66.7Improved
add denoising of GUI understanding data (ablation)UIPro-SLiME · RefExpgrounding accuracy: 43.5 -> 45.8Improved
add denoising of GUI understanding data (ablation)UIPro-SLiME · VWB AGgrounding accuracy: 32.0 -> 34.0Improved
add 20.6M GUI understanding pre-training data (vs none) (ablation)UIPro-SLiME · OmniAct-DesktopStep SR: 15.4 -> 25.1Improved
add 5.9M GUI understanding pre-training data (vs none) (ablation)UIPro-SLiME · OmniAct-DesktopStep SR: 15.4 -> 18.9Improved
scale pre-training data from 5.9M to 20.6M (ablation)UIPro-SLiME · OmniAct-DesktopStep SR: 18.9 -> 25.1Improved
add unified action space data sources to fine-tuning (ablation)UIPro-7B · AndroidControl-High (Swipe)action accuracy: 22.6 -> 50.9Improved
add unified action space data sources to fine-tuning (ablation)UIPro-7B · AndroidControl-High (Wait)action accuracy: 43.6 -> 73.4Improved
add unified action space data sources to fine-tuning (ablation)UIPro-7B · GUIAct (Answer)action accuracy: 12.6 -> 43.0Improved
unify action spaces when mixing data sources (ablation)UIPro · AITW/AndroidControl/GUIActStep SRImproved
add pre-training on GUI understanding data (ablation)UIPro · GUI agent benchmarksStep SRImproved
use UIPro-Qwen2VL instead of OS-ATLASUIPro-Qwen2VL-7B · AITWOverall step SR: 63.1 -> 70.4Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy