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

Source: [VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents](<https://www.sota2.com/research/paper/68fa7b691e209131cea8842b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-07T05:00:04.607Z

Authors: Zheng Wu, Heyuan Huang, Xingyu Lou, Xiangmou Qu, Pengzhou Cheng, Zongru Wu, Weiwen Liu, Weinan Zhang, Jun Wang, Zhaoxiang Wang, Zhuosheng Zhang

Published: 2025-09-09T09:46:01.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [OS agent GUI interaction on VeriOS-Bench](<https://www.sota2.com/research/sota/os-agent-gui-interaction-on-verios-bench.md>): OS agent GUI interaction; VeriOS-Bench; MC Score: 47.62.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.07553>)

[PDF](<https://arxiv.org/pdf/2509.07553.pdf>)