Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents

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 harder to enforce. An agent touches many data sources, runs multi-step workflows, keeps state across sessions, and acts with delegated permissions. Sensitive information can therefore leak not only through its final answer but through the queries it

Categories

Framework mappings

Suggested from the entry's categories.

@misc{lahjouji2026agents,
  title = {{Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents}},
  author = {Nada Lahjouji and Ashwin Gerard Colaco},
  year = {2026},
  month = jun,
  eprint = {2606.26627},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.26627}
}