Tag
This paper builds a streaming-recall benchmark that separates an agent's query-independent retention decision from its query-aware selection decision, showing that much of a prior evaluation's reported memory advantage was actually an access-regime artifact and that recall under bounded memory is upper-bounded by retention rate.
CAFE is an open-source platform that applies design-of-experiments principles to evaluate compound AI systems, attributing answer quality variance to components and their interactions using factorial designs and mixed-effects models.