Paper Detail

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

Chengshuai Yang

arxiv Score 7.6

Published 2026-03-26 · First seen 2026-03-27

General AI

Abstract

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 introduce spec.md, a structured specification format, and three autonomous agents -- Plan, Judge, and Execute -- that translate a one-sentence 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 to a corrective action. On 6 real-data modalities spanning all 5 carrier families, the automated pipeline matches expert-library quality (98.1 +/- 4.2%). Ten novel designs -- composing primitives into chains from 3D to 5D -- demonstrate compositional reach beyond any single-modality tool.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{yang2026designing,
  title = {Designing Any Imaging System from Natural Language: Agent-Constrained Composition over a Finite Primitive Basis},
  author = {Chengshuai Yang},
  year = {2026},
  abstract = {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 introduce spec.md, a structured specification format, and three autonomous agents -- Plan, Judge, and Execute -- that translate a one-sentence natural-language description into a validated forward model with bounded re},
  url = {https://arxiv.org/abs/2603.25636},
  keywords = {cs.CV},
  eprint = {2603.25636},
  archiveprefix = {arXiv},
}

Metadata

{}