VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Zheng, Huang, Heyuan, Lou, Xingyu, Qu, Xiangmou, Cheng, Pengzhou, Wu, Zongru, Liu, Weiwen, Zhang, Weinan, Wang, Jun, Wang, Zhaoxiang, Zhang, Zhuosheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917381237899264
author Wu, Zheng
Huang, Heyuan
Lou, Xingyu
Qu, Xiangmou
Cheng, Pengzhou
Wu, Zongru
Liu, Weiwen
Zhang, Weinan
Wang, Jun
Wang, Zhaoxiang
Zhang, Zhuosheng
author_facet Wu, Zheng
Huang, Heyuan
Lou, Xingyu
Qu, Xiangmou
Cheng, Pengzhou
Wu, Zongru
Liu, Weiwen
Zhang, Weinan
Wang, Jun
Wang, Zhaoxiang
Zhang, Zhuosheng
contents With the rapid progress of multimodal large language models, operating system (OS) agents become increasingly capable of automating tasks through on-device graphical user interfaces (GUIs). However, most existing OS agents are designed for idealized settings, whereas real-world environments often present untrustworthy conditions. To mitigate risks of over-execution in such scenarios, we propose a query-driven human-agent-GUI interaction framework that enables OS agents to decide when to query humans for more reliable task completion. Built upon this framework, we introduce VeriOS-Agent, a trustworthy OS agent trained with a three-stage learning paradigm that falicitate the decoupling and utilization of meta-knowledge by supervised fine-tuning and group relative policy optimization. Concretely, VeriOS-Agent autonomously executes actions in normal conditions while proactively querying humans in untrustworthy scenarios. Experiments show that VeriOS-Agent improves the average step-wise success rate by 19.72\% in over the strongest baselines, without compromising normal performance. VeriOS-Agent significantly improves performance in untrustworthy scenarios while maintaining comparable performance in trustworthy scenarios. Analysis highlights VeriOS-Agent's rationality, generalizability, and scalability. The codes, datasets and models are available at https://github.com/Wuzheng02/VeriOS.
format Preprint
id arxiv_https___arxiv_org_abs_2509_07553
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents
Wu, Zheng
Huang, Heyuan
Lou, Xingyu
Qu, Xiangmou
Cheng, Pengzhou
Wu, Zongru
Liu, Weiwen
Zhang, Weinan
Wang, Jun
Wang, Zhaoxiang
Zhang, Zhuosheng
Computation and Language
With the rapid progress of multimodal large language models, operating system (OS) agents become increasingly capable of automating tasks through on-device graphical user interfaces (GUIs). However, most existing OS agents are designed for idealized settings, whereas real-world environments often present untrustworthy conditions. To mitigate risks of over-execution in such scenarios, we propose a query-driven human-agent-GUI interaction framework that enables OS agents to decide when to query humans for more reliable task completion. Built upon this framework, we introduce VeriOS-Agent, a trustworthy OS agent trained with a three-stage learning paradigm that falicitate the decoupling and utilization of meta-knowledge by supervised fine-tuning and group relative policy optimization. Concretely, VeriOS-Agent autonomously executes actions in normal conditions while proactively querying humans in untrustworthy scenarios. Experiments show that VeriOS-Agent improves the average step-wise success rate by 19.72\% in over the strongest baselines, without compromising normal performance. VeriOS-Agent significantly improves performance in untrustworthy scenarios while maintaining comparable performance in trustworthy scenarios. Analysis highlights VeriOS-Agent's rationality, generalizability, and scalability. The codes, datasets and models are available at https://github.com/Wuzheng02/VeriOS.
title VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents
topic Computation and Language
url https://arxiv.org/abs/2509.07553