Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915931203043328 |
|---|---|
| author | Zhu, Jiachen Yang, Lingyu Shan, Rong Zheng, Congmin Zheng, Zeyu Liu, Weiwen Yu, Yong Zhang, Weinan Lin, Jianghao |
| author_facet | Zhu, Jiachen Yang, Lingyu Shan, Rong Zheng, Congmin Zheng, Zeyu Liu, Weiwen Yu, Yong Zhang, Weinan Lin, Jianghao |
| contents | The rise of autonomous GUI agents has triggered adversarial countermeasures from digital platforms, yet existing research prioritizes utility and robustness over the critical dimension of anti-detection. We argue that for agents to survive in human-centric ecosystems, they must evolve Humanization capabilities. We introduce the ``Turing Test on Screen,'' formally modeling the interaction as a MinMax optimization problem between a detector and an agent aiming to minimize behavioral divergence. We then collect a new high-fidelity dataset of mobile touch dynamics, and conduct our analysis that vanilla LMM-based agents are easily detectable due to unnatural kinematics. Consequently, we establish the Agent Humanization Benchmark (AHB) and detection metrics to quantify the trade-off between imitability and utility. Finally, we propose methods ranging from heuristic noise to data-driven behavioral matching, demonstrating that agents can achieve high imitability theoretically and empirically without sacrificing performance. This work shifts the paradigm from whether an agent can perform a task to how it performs it within a human-centric ecosystem, laying the groundwork for seamless coexistence in adversarial digital environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09574 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization Zhu, Jiachen Yang, Lingyu Shan, Rong Zheng, Congmin Zheng, Zeyu Liu, Weiwen Yu, Yong Zhang, Weinan Lin, Jianghao Artificial Intelligence Machine Learning The rise of autonomous GUI agents has triggered adversarial countermeasures from digital platforms, yet existing research prioritizes utility and robustness over the critical dimension of anti-detection. We argue that for agents to survive in human-centric ecosystems, they must evolve Humanization capabilities. We introduce the ``Turing Test on Screen,'' formally modeling the interaction as a MinMax optimization problem between a detector and an agent aiming to minimize behavioral divergence. We then collect a new high-fidelity dataset of mobile touch dynamics, and conduct our analysis that vanilla LMM-based agents are easily detectable due to unnatural kinematics. Consequently, we establish the Agent Humanization Benchmark (AHB) and detection metrics to quantify the trade-off between imitability and utility. Finally, we propose methods ranging from heuristic noise to data-driven behavioral matching, demonstrating that agents can achieve high imitability theoretically and empirically without sacrificing performance. This work shifts the paradigm from whether an agent can perform a task to how it performs it within a human-centric ecosystem, laying the groundwork for seamless coexistence in adversarial digital environments. |
| title | Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2604.09574 |