移动图形界面代理的隐私个性化：基于轨迹诱导的偏好优化

Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization

April 13, 2026

作者: Zhixin Lin, Jungang Li, Dongliang Xu, Shidong Pan, Yibo Shi, Yuchi Liu, Yuecong Min, Yue Yao

cs.AI

摘要

基于多模态大语言模型（MLLMs）的移动端图形界面代理能够在移动设备上执行复杂任务。尽管取得这些进展，现有系统大多仍以任务成功率或效率为优化目标，忽视了用户的隐私个性化需求。本文研究了这一常被忽视的代理个性化问题，发现个性化会导致执行轨迹出现系统性结构异质性。例如，隐私优先型用户往往倾向于采取防护性操作（如拒绝权限、退出登录、最小化信息暴露），其执行轨迹与效用优先型用户存在逻辑差异。此类变长且结构相异的轨迹会使标准偏好优化方法稳定性下降、信息量减少。为解决该问题，我们提出轨迹诱导偏好优化（TIPO）方法：通过偏好强度加权强化关键隐私步骤，利用填充门控抑制对齐噪声。在隐私偏好数据集上的实验表明，TIPO在保持强任务执行能力的同时显著提升了人格对齐度与区分度，以65.60%的任务成功率、46.22%的合规率及66.67%的人格区分度优于现有优化方法，在各种图形界面任务中均表现优异。代码与数据集将发布于https://github.com/Zhixin-L/TIPO。

English

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.