arXiv cs.AIOctober 2, 2026
Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
Excerpt
arXiv:2610.00371v1 Announce Type: cross Abstract: Multi-agent systems derive their capabilities from sharing evidence, delegating tasks, and combining information across agents. The same process creates a safety problem: contributions that are admissible in isolation can jointly enable a prohibited use. Blocking every sensitive action avoids disclosure but defeats the purpose of collaboration. We introduce authorization-paired evaluation, which makes blocking prohibited uses and completing requi