---
id: 20260415-T0-14
title: "Turing Test on Screen：移动GUI代理人性化评测基准"
title_en: "Turing Test on Screen: Benchmark for Mobile GUI Agent Humanization"
url: https://ai.daily.yangsir.net/daily/20260415-T0-14
issue_date: 2026-04-15
publish_date: 2026-04-14T04:00:00.000Z
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2604.09574
---

# Turing Test on Screen：移动GUI代理人性化评测基准

论文提出移动GUI代理人性化评测基准，专注于反检测能力。研究指出，现有研究过于重视效用和鲁棒性，而忽视了关键的防屏蔽维度，该基准为评估代理的拟人化程度提供了新标准。

## English Version

**Turing Test on Screen: Benchmark for Mobile GUI Agent Humanization**

A paper introduces a benchmark for evaluating mobile GUI agents' humanization, focusing on anti-detection capabilities. The research argues existing work prioritizes utility and robustness while ignoring critical anti-detection aspects, providing a new standard for assessing agent humanness.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2604.09574)

**详情页**：https://ai.daily.yangsir.net/daily/20260415-T0-14

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*