PulseAugur
EN
LIVE 13:13:43

New DragOn dataset boosts GUI agent drag-and-drop capabilities

By PulseAugur Editorial · [2 sources] ·

Researchers have introduced DragOn, a new benchmark and dataset designed to improve the performance of GUI agents in handling drag-based interactions. The dataset includes 286,000 training screenshots and 3.5 million training tasks across four domains: text highlighting, cell selection, element resizing, and slider manipulation. Evaluations of various proprietary and open-weight models, including GPT, Claude, Qwen, and Kimi, indicate that fine-tuning on DragOn can enhance their capabilities in complex drag-and-drop and similar GUI operations. AI

IMPACT Enhances GUI agent capabilities for automating digital tasks, potentially improving user experience and efficiency.

RANK_REASON The cluster contains an academic paper introducing a new benchmark and dataset for AI research.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New DragOn dataset boosts GUI agent drag-and-drop capabilities

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Nathan Bout, Maxime Langevin, Ronan Riochet ·

    DragOn: A Benchmark and Dataset for Drag-Based GUI Interactions

    arXiv:2606.06322v1 Announce Type: new Abstract: GUI agents - vision-based models that control desktops, web browsers, and mobile devices through graphical user interfaces - promise to automate a wide range of digital tasks. While million-scale datasets have enabled substantial pr…

  2. arXiv cs.AI TIER_1 English(EN) · Ronan Riochet ·

    DragOn: A Benchmark and Dataset for Drag-Based GUI Interactions

    GUI agents - vision-based models that control desktops, web browsers, and mobile devices through graphical user interfaces - promise to automate a wide range of digital tasks. While million-scale datasets have enabled substantial progress on click-grounding, drag grounding (e.g. …

RELATED ENTITIES

RELATED TOPICS