arXiv Artificial Intelligence

PrivacySkills: How Privacy Guidance Shapes Source Selection in LLM Agents

PrivacySkills: How Privacy Guidance Shapes Source Selection in LLM Agents

Quick summary

arXiv:2609.35937v1 Announce Type: cross Abstract: While prior work has documented privacy failures in LLM agents, it remains unclear how the presentation of privacy guidance influences their choice of information sources. We introduce PrivacySkills, a controlled framework for evaluating how agents choose among acquisition pathways that provide the same task-relevant value: consulting publicly available personal information, accessing confidential sources, or interacting with the user. The evaluation framework comprises 55 synthetic tasks spanning 11 categories of personal information, with 169

Key takeaways

  • arXiv:2609.35937v1 Announce Type: cross Abstract: While prior work has documented privacy failures in LLM agents, it remains unclear how the presentation of privacy guidance influences their choice of information sources.
  • We introduce PrivacySkills, a controlled framework for evaluating how agents choose among acquisition pathways that provide the same task-relevant value: consulting publicly available personal information, accessing confidential sources, or interacting with the user.
  • The evaluation framework comprises 55 synthetic tasks spanning 11 categories of personal information, with 169

Why it matters

The significance is not only the legal text but how it changes product design. Decisions around “PrivacySkills: How Privacy Guidance Shapes Source Selection in LLM Agents” may reshape data collection, model training, output accountability and market access.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗