Security Considerations for Multi-agent Systems

arXiv:2603.09002v2 Announce Type: replace-cross Abstract: Multi-agent artificial intelligence systems or MAS are systems of autonomous agents that exercise delegated tool authority, share persistent memory, and coordinate via inter-agent communication. MAS introduces qualitatively distinct security vulnerabilities from those documented for singular AI models. Existing security and governance frameworks were not designed for these emerging attack surfaces. This study systematically characterizes