← Back ◬ AI & Machine Learning Mar 30, 2026

IncreRTL: Traceability-Guided Incremental RTL Generation under Requirement Evolution

arXiv AI Archived Mar 30, 2026 ✓ Full text saved

arXiv:2603.25769v1 Announce Type: cross Abstract: 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 affec

Full text archived locally

✦ AI Summary · Claude Sonnet

Computer Science > Software Engineering [Submitted on 26 Mar 2026] IncreRTL: Traceability-Guided Incremental RTL Generation under Requirement Evolution Luanrong Chen, Renzhi Chen, Xinyu Li, Shanshan Li, Rui Gong, Lei Wang 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. Subjects: Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Hardware Architecture (cs.AR) Cite as: arXiv:2603.25769 [cs.SE] (or arXiv:2603.25769v1 [cs.SE] for this version) https://doi.org/10.48550/arXiv.2603.25769 Focus to learn more Submission history From: Luanrong Chen [view email] [v1] Thu, 26 Mar 2026 08:02:39 UTC (814 KB) Access Paper: HTML (experimental) view license Current browse context: cs.SE < prev | next > new | recent | 2026-03 Change to browse by: cs cs.AI cs.AR References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

💬 Team Notes