Papers
arxiv:2509.07553

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

Published on Sep 9, 2025
Authors:
,
,
,
,
,
,
,
,

Abstract

VeriOS-Agent, a trustworthy OS agent, uses a query-driven framework and two-stage learning to improve task completion in untrustworthy environments without affecting normal performance.

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 two-stage learning paradigm that falicitate the decoupling and utilization of meta-knowledge. 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 20.64\% in untrustworthy scenarios over the state-of-the-art, without compromising normal performance. Analysis highlights VeriOS-Agent's rationality, generalizability, and scalability. The codes, datasets and models are available at https://github.com/Wuzheng02/VeriOS.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2509.07553
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2509.07553 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.