Salvato in:
Dettagli Bibliografici
Autori principali: Du, Yali, Xi, San-Zhuo, Sun, Hui, Li, Ming
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2603.12712
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915858795724800
author Du, Yali
Xi, San-Zhuo
Sun, Hui
Li, Ming
author_facet Du, Yali
Xi, San-Zhuo
Sun, Hui
Li, Ming
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_12712
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Design-Specification Tiling for ICL-based CAD Code Generation
Du, Yali
Xi, San-Zhuo
Sun, Hui
Li, Ming
Software Engineering
Machine Learning
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.
title Design-Specification Tiling for ICL-based CAD Code Generation
topic Software Engineering
Machine Learning
url https://arxiv.org/abs/2603.12712