Paper Detail
Hongxin Li, Xiping Wang, Jingran Su, Zheng Ju, Yuntao Chen, Qing Li, Zhaoxiang Zhang
Autonomous agents capable of navigating Graphical User Interfaces (GUIs) hold the potential to revolutionize digital productivity. However, achieving true digital autonomy extends beyond reactive element matching; it necessitates a predictive mental model of interface dynamics and the ability to foresee the "digital world state" resulting from interactions. Despite the perceptual capabilities of modern Vision-Language Models (VLMs), existing benchmarks remain bifurcated (focusing either on black-box task completion or static, shallow grounding), thereby failing to assess whether agents truly comprehend the implicit functionality and transition logic of GUIs. To bridge this gap, we introduce AutoGUI-v2, a comprehensive benchmark designed to evaluate deep GUI functionality understanding and interaction outcome prediction. We construct the benchmark using a novel VLM-human collaborative pipeline that recursively parses multi-platform screenshots into hierarchical functional regions to generate diverse evaluation tasks. Providing 2,753 tasks across six operating systems, AutoGUI-v2 rigorously tests agents on region and element-level semantics, grounding, and dynamic state prediction. Our evaluation reveals a striking dichotomy in VLMs: while open-source models fine-tuned on agent data (e.g., Qwen3-VL) excel at functional grounding, commercial models (e.g., Gemini-2.5-Pro-Thinking) dominate in functionality captioning. Crucially, all models struggle with complex interaction logic of uncommon actions, highlighting that deep functional understanding remains a significant hurdle. By systematically measuring these foundational capabilities, AutoGUI-v2 offers a new lens for advancing the next generation of GUI agents.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{li2026autogui,
title = {AutoGUI-v2: A Comprehensive Multi-Modal GUI Functionality Understanding Benchmark},
author = {Hongxin Li and Xiping Wang and Jingran Su and Zheng Ju and Yuntao Chen and Qing Li and Zhaoxiang Zhang},
year = {2026},
abstract = {Autonomous agents capable of navigating Graphical User Interfaces (GUIs) hold the potential to revolutionize digital productivity. However, achieving true digital autonomy extends beyond reactive element matching; it necessitates a predictive mental model of interface dynamics and the ability to foresee the "digital world state" resulting from interactions. Despite the perceptual capabilities of modern Vision-Language Models (VLMs), existing benchmarks remain bifurcated (focusing either on black},
url = {https://huggingface.co/papers/2604.24441},
keywords = {Vision-Language Models, GUI navigation, digital autonomy, mental model, interface dynamics, digital world state, benchmark, VLM-human collaborative pipeline, multi-platform screenshots, functional regions, semantic grounding, dynamic state prediction, agent data, functionality captioning, interaction logic, code available, huggingface daily},
eprint = {2604.24441},
archiveprefix = {arXiv},
}
{}