Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents
Large language model agents are increasingly deployed as autonomous loops. Starting from one human goal, such a system repeatedly discovers work, plans, executes tool calls, verifies outcomes and persists state across many unattended iterations. The agent safeguards in wide use, however, are defined over a single trajectory, and their safety state is re-initialized when the next trajectory…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
