用自然语言自动设计成像系统，实现专家级精度。
Designing Any Imaging System from Natural Language: Agent-Constrained Composition over a Finite Primitive Basis
- 三类智能代理协同解析指令，生成可验证的成像模型。
- 在6种真实模态上达到98.1%±4.2%的专家级重建质量。
- 支持从3D到5D的复合结构设计，突破单模态限制。
设计计算成像系统——选择算子、设置参数、验证一致性——每种模态需数周专业人力，形成知识壁垒，阻碍科学界快速原型开发。本文提出spec.md结构化规范格式与三个自主代理（规划、评估、执行），将一句自然语言描述转化为具有有限重构误差的验证后向模型。设计到现实的误差定理将总重构误差分解为五个独立可约束项，每项对应一种修正动作。在涵盖5类载体的6个真实数据模态上，自动化流程达到专家库水平（98.1±4.2%）。十种新设计通过组合基元构成3D至5D链式结构，展示超越单一模态工具的组合能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。