AI ethics evidence index Search
Source-linked daily record
Evidence record 583 · automatically gathered

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

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

Record details

Published: 25 June 2026
Source: arXiv
Category: Research
Topics: Privacy · Agents & autonomy
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Privacy · Shared topic: Agents & autonomy

Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning

arXiv · 25 June 2026

Shared topic: Privacy · Shared topic: Agents & autonomy

AI Snitches Get Glitches: Towards Evading Agentic Surveillance

arXiv · 24 June 2026

Shared topic: Privacy · Shared topic: Agents & autonomy

Digitizing Coaching Intelligence: An Agentic Framework for Holistic Athlete Profiling using VLM and RAG

arXiv · 26 June 2026

Shared topic: Privacy · Shared topic: Agents & autonomy

Governed Shared Memory for Multi-Agent LLM Systems

arXiv · 23 June 2026

Shared topic: Privacy · Shared topic: Agents & autonomy

Self-Evolution for Multi-Turn Tool-Calling Agents via Divergence-Point Preference Learning

arXiv · 22 June 2026

Shared topic: Privacy · Shared topic: Agents & autonomy

Recent advances in AI-based mobile robots for human companionship: survey

Artificial Intelligence Review · 29 June 2026

How to cite this record

ethics.ai (25 June 2026), “Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents,” evidence record 583, https://ethics.ai/record/583 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.