Modern LLM-powered autonomous agents increasingly rely on rich user interface (UI) state observations to achieve reliable action grounding in complex digital environments. However, many deployments transmit the full UI state to remote inference servers even when most elements are irrelevant to the current task, which can leak sensitive but unnecessary context such as authentication codes, private notifications, and background application states. We propose MINIM, a trusted local broker that performs privacy-aware minimization on the client side before any observation leaves the device. Grounded in Contextual Integrity (CI), MINIM learns a dual-score representation for each UI element by predicting an inherent sensitivity score (s) and a task-conditioned necessity score (n). These scores drive a ternary disclosure policy that keeps essential elements, abstracts sensitive attributes when needed, and removes task-irrelevant content. We optimize a CI-aware objective that penalizes necessity errors more strongly on high-risk content, enabling aggressive pruning while preserving task-critical information. Experiments on real-world UI observations derived from WebArena show that MINIM substantially reduces task-irrelevant sensitive leakage while preserving task-critical semantic context and the interactive affordances required for reliable agent actions.

翻译：摘要：现代基于大语言模型的自主智能体日益依赖丰富的用户界面状态观测，以在复杂数字环境中实现可靠的动作锚定。然而，许多部署方案会将完整的UI状态传输至远程推理服务器，即便其中大部分元素与当前任务无关，这可能导致敏感但非必要上下文（如认证码、隐私通知及后台应用状态）的泄露。我们提出MINIM——一种在观测数据离设备前执行客户端侧隐私感知最小化的可信本地中介。基于情境完整性理论，MINIM通过为每个UI元素预测固有敏感度分数（s）与任务条件必要性分数（n），学习其双分数表示。这些分数驱动三项披露策略：保留核心元素，必要时抽象敏感属性，并移除与任务无关内容。我们优化了具备情境完整性感知的目标函数，其中对高风险内容中必要性预测偏差的惩罚更为严格，从而在保留任务关键信息的同时实现激进修剪。基于WebArena衍生的真实UI观测实验表明，MINIM在显著减少与任务无关的敏感信息泄露的同时，保留了任务关键语义上下文及可靠智能体动作所需的交互功能。