Design-Specification Tiling for ICL-based CAD Code Generation

TL;DR

This paper introduces Design-Specification Tiling (DST), a novel exemplar selection method for ICL in CAD code generation, which improves performance by ensuring comprehensive coverage of design specifications.

Contribution

The paper proposes a knowledge sufficiency objective and DST method for exemplar selection, addressing redundancy and coverage issues in ICL for CAD tasks.

Findings

DST outperforms existing selection strategies in CAD code generation quality.

Maximizing the tiling ratio improves the coverage of design components.

The greedy algorithm provides a (1-1/e)-approximation guarantee.

Abstract

Large language models (LLMs) have demonstrated remarkable capabilities in code generation, yet they underperform on domain-specific tasks such as Computer-Aided Design (CAD) code generation due to scarce training data. In-Context Learning (ICL) offers a training-free alternative through task-specific exemplars. However, existing selection strategies prioritize similarity or point-wise diversity, often producing redundant selections that fail to satisfy the compositional requirements of complex CAD design specifications. In this work, we propose knowledge sufficiency as a principled objective for exemplar selection that aims to maximally satisfy all requirements within design specifications. To realize this objective, we introduce Design-Specification Tiling (DST), which quantifies knowledge sufficiency through a surrogate tiling ratio by extracting multi-granular design components and measuring the proportion of query components covered by selected exemplars. We demonstrate that maximizing this objective constitutes submodular maximization and provide a polynomial-time greedy algorithm with a (1-1/e)-approximation guarantee. Extensive experiments demonstrate that DST substantially improves CAD code generation quality, consistently outperforming existing exemplar selection strategies in ICL.