让手机助手更懂用户隐私偏好，自动调整操作风格。
Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization
- 根据用户隐私偏好动态调整操作路径，识别保护性行为
- 在多类任务中实现65.6%任务成功率与46.2%合规率
- 适合关注隐私安全的移动智能助手研究者使用
由多模态大语言模型驱动的移动端GUI代理可执行复杂任务。尽管取得进展，现有系统仍主要优化任务成功率或效率，忽视了用户隐私个性化需求。本文研究这一被忽略的问题，发现个性化会导致执行轨迹出现系统性结构差异：注重隐私的用户倾向于拒绝权限、退出登录、减少暴露等防护行为，形成逻辑上不同于追求效率用户的轨迹。这类变长且结构不同的轨迹使标准偏好优化不稳定且信息量不足。为此，我们提出轨迹诱导偏好优化（TIPO），通过偏好强度加权突出关键隐私步骤，并利用填充门控抑制对齐噪声。在自建的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，显著提升人格化对齐与区分度，达成65.60%成功率、46.22%合规率和66.67%个人化度，优于现有方法。代码与数据集将公开于https://github.com/Zhixin-L/TIPO。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。