most citedArchitecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations

1 citations · 1 across the 3 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring

Usman Anwar, Julianna Piskorz, David D. Baek +6

Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanisms. Yet principled methods to de…