Only as Safe as the Weakest Agent: A Break That Appears Only When the System Is Multi-Agent

The point

Researchers planted a forged record in files on disk and asked agents to answer from that store. Strong orchestrators searching themselves made almost zero harmful revisions in over 1,000 trials. When they delegated to a cheaper sub-agent, the same models failed on up to 553 of 900 trials.

Why it matters

For builders, safety is set by your weakest sub-agent, not your strongest model.

Key details

Original ~8 min → 25 sec here Source: arXiv cs.AI, Nov 16, 2026

← All points