Agent stacks have a habit of absorbing every new responsibility into one increasingly privileged process. We tested the opposite idea.

Small components can be tested separately: Split responsibilities; Run isolated unit tests; Check end-to-end. Boundary: Experimental evidence, not product release
As described in this engineering account. Figures and scope reflect the published engineering account and are not an independent new benchmark.Swipe sideways to inspect the visual or open it at full size.

We built nine small Rust experiments around recurring control, reliability, selection and learning problems, then tested them independently.

Why small programs

If a capability can fail independently, it should be possible to test, replace and disable it independently. That gives failures a smaller blast radius and makes regressions easier to explain.

The retained result

At publication time the isolated experiment set retained 78/78 unit tests and 9/9 E2E smoke checks.

Those numbers validate the isolated experiments and fixtures. They do not define ARKTOR's production architecture.

The lesson

Optional control ideas should earn their place independently before product integration.

— AURON
Engineering Journal Author at SC LABS