Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917403003191296 |
|---|---|
| author | Lin, Zhixin Li, Jungang Xu, Dongliang Pan, Shidong Shi, Yibo Liu, Yuchi Min, Yuecong Yao, Yue |
| author_facet | Lin, Zhixin Li, Jungang Xu, Dongliang Pan, Shidong Shi, Yibo Liu, Yuchi Min, Yuecong Yao, Yue |
| contents | Mobile GUI agents powered by Multimodal Large Language Models (MLLMs) can execute complex tasks on mobile devices. Despite this progress, most existing systems still optimize task success or efficiency, neglecting users' privacy personalization. In this paper, we study the often-overlooked problem of agent personalization. We observe that personalization can induce systematic structural heterogeneity in execution trajectories. For example, privacy-first users often prefer protective actions, e.g., refusing permissions, logging out, and minimizing exposure, leading to logically different execution trajectories from utility-first users. Such variable-length and structurally different trajectories make standard preference optimization unstable and less informative. To address this issue, we propose Trajectory Induced Preference Optimization (TIPO), which uses preference-intensity weighting to emphasize key privacy-related steps and padding gating to suppress alignment noise. Results on our Privacy Preference Dataset show that TIPO improves persona alignment and distinction while preserving strong task executability, achieving 65.60% SR, 46.22 Compliance, and 66.67% PD, outperforming existing optimization methods across various GUI tasks. The code and dataset will be publicly released at https://github.com/Zhixin-L/TIPO. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_11259 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization Lin, Zhixin Li, Jungang Xu, Dongliang Pan, Shidong Shi, Yibo Liu, Yuchi Min, Yuecong Yao, Yue Artificial Intelligence Cryptography and Security Mobile GUI agents powered by Multimodal Large Language Models (MLLMs) can execute complex tasks on mobile devices. Despite this progress, most existing systems still optimize task success or efficiency, neglecting users' privacy personalization. In this paper, we study the often-overlooked problem of agent personalization. We observe that personalization can induce systematic structural heterogeneity in execution trajectories. For example, privacy-first users often prefer protective actions, e.g., refusing permissions, logging out, and minimizing exposure, leading to logically different execution trajectories from utility-first users. Such variable-length and structurally different trajectories make standard preference optimization unstable and less informative. To address this issue, we propose Trajectory Induced Preference Optimization (TIPO), which uses preference-intensity weighting to emphasize key privacy-related steps and padding gating to suppress alignment noise. Results on our Privacy Preference Dataset show that TIPO improves persona alignment and distinction while preserving strong task executability, achieving 65.60% SR, 46.22 Compliance, and 66.67% PD, outperforming existing optimization methods across various GUI tasks. The code and dataset will be publicly released at https://github.com/Zhixin-L/TIPO. |
| title | Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization |
| topic | Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2604.11259 |