LLM生成代码时可随需求变化自动更新，避免重写全部代码
IncreRTL: Traceability-Guided Incremental RTL Generation under Requirement Evolution
- 通过追踪需求与代码的关联，只重生成受影响部分
- 在新构建的数据集上，更新一致性提升显著，效率更高
- 适合需要频繁修改的芯片设计场景，提升工程实用性
大型语言模型（LLMs）在从自然语言描述生成RTL代码方面展现出潜力，但现有方法仍为静态模式，难以适应不断演化的设计需求，可能导致结构漂移并引发高昂的全量重生成成本。我们提出IncreRTL，一种基于LLM的增量式RTL生成框架，可在需求演化下实现精准更新。通过构建需求-代码间的可追溯链接，定位并仅重生成受影响的代码片段，确保更新的准确性和一致性。在我们新构建的EvoRTL-Bench数据集上评估显示，IncreRTL在再生一致性和效率方面均有显著提升，推动基于LLM的RTL生成向实际工程部署迈进。
原文摘要 · Abstract (English)
Large language models (LLMs) have shown promise in generating RTL code from natural-language descriptions, but existing methods remain static and struggle to adapt to evolving design requirements, potentially causing structural drift and costly full regeneration. We propose IncreRTL, a LLM-driven framework for incremental RTL generation under requirement evolution. By constructing requirement-code traceability links to locate and regenerate affected code segments, IncreRTL achieves accurate and consistent updates. Evaluated on our newly constructed EvoRTL-Bench, IncreRTL demonstrates notable improvements in regeneration consistency and efficiency, advancing LLM-based RTL generation toward practical engineering deployment.
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。