GUI Knowledge Bench: Revealing the Knowledge Gap of VLMs in GUI Tasks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shi, Chenrui, Yu, Zedong, Gao, Zhi, Feng, Ruining, Liu, Enqi, Wu, Yuwei, Jia, Yunde, Xiang, Liuyu, He, Zhaofeng, Li, Qing
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908821730885632
author Shi, Chenrui
Yu, Zedong
Gao, Zhi
Feng, Ruining
Liu, Enqi
Wu, Yuwei
Jia, Yunde
Xiang, Liuyu
He, Zhaofeng
Li, Qing
author_facet Shi, Chenrui
Yu, Zedong
Gao, Zhi
Feng, Ruining
Liu, Enqi
Wu, Yuwei
Jia, Yunde
Xiang, Liuyu
He, Zhaofeng
Li, Qing
contents Vision language models (VLMs) have advanced graphical user interface (GUI) task automation but still lag behind humans. We hypothesize this gap stems from missing core GUI knowledge, which existing training schemes (such as supervised fine tuning and reinforcement learning) alone cannot fully address. By analyzing common failure patterns in GUI task execution, we distill GUI knowledge into three dimensions: (1) interface knowledge about widget functions, layout semantics, and system states; (2) interaction knowledge about GUI interaction types and effects; and (3) procedure knowledge of task objectives and workflow sequences. We further introduce GUI Knowledge Bench, a benchmark with multiple-choice and yes/no questions across six platforms (Web, Android, MacOS, Windows, Linux, IOS) and 292 applications. Our evaluation indicates that current VLMs are generally aware of the functions of individual widgets, but lack the GUI-specific knowledge required to track system states, adhere to GUI interaction conventions, and assess task completion progress. Experiments on real-world GUI tasks further validate the close link between GUI knowledge and task success. By providing a structured framework for assessing GUI knowledge, our work supports the selection of VLMs with greater potential prior to downstream training and provides insights for building more capable GUI agents.
format Preprint
id arxiv_https___arxiv_org_abs_2510_26098
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GUI Knowledge Bench: Revealing the Knowledge Gap of VLMs in GUI Tasks
Shi, Chenrui
Yu, Zedong
Gao, Zhi
Feng, Ruining
Liu, Enqi
Wu, Yuwei
Jia, Yunde
Xiang, Liuyu
He, Zhaofeng
Li, Qing
Artificial Intelligence
Vision language models (VLMs) have advanced graphical user interface (GUI) task automation but still lag behind humans. We hypothesize this gap stems from missing core GUI knowledge, which existing training schemes (such as supervised fine tuning and reinforcement learning) alone cannot fully address. By analyzing common failure patterns in GUI task execution, we distill GUI knowledge into three dimensions: (1) interface knowledge about widget functions, layout semantics, and system states; (2) interaction knowledge about GUI interaction types and effects; and (3) procedure knowledge of task objectives and workflow sequences. We further introduce GUI Knowledge Bench, a benchmark with multiple-choice and yes/no questions across six platforms (Web, Android, MacOS, Windows, Linux, IOS) and 292 applications. Our evaluation indicates that current VLMs are generally aware of the functions of individual widgets, but lack the GUI-specific knowledge required to track system states, adhere to GUI interaction conventions, and assess task completion progress. Experiments on real-world GUI tasks further validate the close link between GUI knowledge and task success. By providing a structured framework for assessing GUI knowledge, our work supports the selection of VLMs with greater potential prior to downstream training and provides insights for building more capable GUI agents.
title GUI Knowledge Bench: Revealing the Knowledge Gap of VLMs in GUI Tasks
topic Artificial Intelligence
url https://arxiv.org/abs/2510.26098