Delegated Misalignment: How Multi-Agent Structures Amplify LLM Safety Risks
Large language models (LLMs) are increasingly deployed in multi-agent systems where a principal agent decomposes tasks and delegates them to subordinate agents that may invoke external tools. Safety alignment, however, is still evaluated almost exclusively under a single-agent threat model, treating safety as a property of the individual LLM. We show that this assumption breaks down: \emph{individual safety alignment fails to transfer to multi-agent settings}. Two failure mechanisms emerge under delegation: \emph{responsibility diffusion} on the principal side and \emph{role-bias compliance} on the subordinate side, jointly converting language-level refusal into actionable harm. We refer ...
| Authors | Zonghao Ying, Jiaqi Yan, Huize Luo et al. |
|---|---|
| Primary category | cs.CL |
| Published | 26 August 2026 |
| Last updated at source | 26 August 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.