Current use-case benchmarks are insufficient because they only measure whether one agent completes one task, but fail to capture how changing capabilities, models, runtime mechanisms, capacity, and enterprise data should be managed organizationally.

Use-case benchmarks show whether one agent completes one task, but not how changing capabilities, models, runtime mechanisms, capacity, and enterprise data should be owned, changed, admitted, or evidenced together.

http://arxiv.org/abs/2608.27086v1