PrivAct: Internalizing Contextual Privacy Preservation via Multi-Agent Preference Training

Excerpt

arXiv:2602.13840v2 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly deployed in personalized tasks involving sensitive, context-dependent information, where privacy violations may arise in agents' action due to the implicitness of contextual privacy. Existing approaches rely on external, inference-time interventions which are brittle, scenario-specific, and may expand the privacy attack surface. We propose PrivAct, a contextual privacy-aware multi-agent learnin