Designing Any Imaging System from Natural Language: Agent-Constrained Composition over a Finite Primitive Basis

ArXi:2603.25636v1 Announce Type: new Designing a computational imaging system -- selecting operators, setting parameters, validating consistency -- requires weeks of specialist effort per modality, creating an expertise bottleneck that excludes the broader scientific community from prototyping imaging instruments. We natural-language description into a validated forward model with bounded reconstruction error. A design-to-real error theorem decomposes total reconstruction error into five independently bounded terms, each linked.