arxiv
PublishedSeptember 3, 2026 at 4:00 AM
—neutral
CAPTURE: Disentangling Preference Drift from Memory Poisoning in Personalized LLM Agents
Publisher summary· verbatim
arXiv:2609.02265v1 Announce Type: new Abstract: Personalized language agents use persistent memory to adapt to users over time, but the same mechanism creates an attack surface. When new information conflicts with stored preferences, an agent must distinguish genuine preference drift from temporary
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
The Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗