Saved in:
Bibliographic Details
Main Authors: Cheng, Ziming, Huang, Zhiyuan, Pan, Junting, Hou, Zhaohui, Zhan, Mingjie
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.24180
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916912660742144
author Cheng, Ziming
Huang, Zhiyuan
Pan, Junting
Hou, Zhaohui
Zhan, Mingjie
author_facet Cheng, Ziming
Huang, Zhiyuan
Pan, Junting
Hou, Zhaohui
Zhan, Mingjie
contents Graphical user interfaces (GUI) automation agents are emerging as powerful tools, enabling humans to accomplish increasingly complex tasks on smart devices. However, users often inadvertently omit key information when conveying tasks, which hinders agent performance in the current agent paradigm that does not support immediate user intervention. To address this issue, we introduce a $\textbf{Self-Correction GUI Navigation}$ task that incorporates interactive information completion capabilities within GUI agents. We developed the $\textbf{Navi-plus}$ dataset with GUI follow-up question-answer pairs, alongside a $\textbf{Dual-Stream Trajectory Evaluation}$ method to benchmark this new capability. Our results show that agents equipped with the ability to ask GUI follow-up questions can fully recover their performance when faced with ambiguous user tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2503_24180
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Navi-plus: Managing Ambiguous GUI Navigation Tasks with Follow-up Questions
Cheng, Ziming
Huang, Zhiyuan
Pan, Junting
Hou, Zhaohui
Zhan, Mingjie
Computer Vision and Pattern Recognition
Human-Computer Interaction
Graphical user interfaces (GUI) automation agents are emerging as powerful tools, enabling humans to accomplish increasingly complex tasks on smart devices. However, users often inadvertently omit key information when conveying tasks, which hinders agent performance in the current agent paradigm that does not support immediate user intervention. To address this issue, we introduce a $\textbf{Self-Correction GUI Navigation}$ task that incorporates interactive information completion capabilities within GUI agents. We developed the $\textbf{Navi-plus}$ dataset with GUI follow-up question-answer pairs, alongside a $\textbf{Dual-Stream Trajectory Evaluation}$ method to benchmark this new capability. Our results show that agents equipped with the ability to ask GUI follow-up questions can fully recover their performance when faced with ambiguous user tasks.
title Navi-plus: Managing Ambiguous GUI Navigation Tasks with Follow-up Questions
topic Computer Vision and Pattern Recognition
Human-Computer Interaction
url https://arxiv.org/abs/2503.24180