arxiv
PublishedJune 27, 2026 at 4:00 AM
—neutral
Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents
Publisher summary· verbatim
arXiv:2606.26627v1 Announce Type: cross Abstract: Large language model agents increasingly query databases, search document collections, call external APIs, remember past interactions, and act on a user's behalf. As they move from answering questions to operating over sensitive data, privacy becomes
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivThe Steering Budget: Examples beat Knobs14harxivPolestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs14harxivRxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination14harxivWhen a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models14hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗