Minim: Privacy-Aware Minimal View for Agents via Trusted Local Sanitization

Computer Science > Artificial Intelligence [Submitted on 11 Jun 2026] Minim: Privacy-Aware Minimal View for Agents via Trusted Local Sanitization Hexuan Yu, Chaoyu Zhang, Heng Jin, Shanghao Shi, Ning Zhang, Y. Thomas Hou, Wenjing Lou 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. Comments: Accepted at ICML 2026 (43rd International Conference on Machine Learning, Seoul, South Korea). Code available at this https URL Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2606.13949 [cs.AI]   (or arXiv:2606.13949v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.13949 Focus to learn more Submission history From: Chaoyu Zhang [view email] [v1] Thu, 11 Jun 2026 22:27:27 UTC (984 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)