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.
@article{arxiv.2603.25769,
title = {IncreRTL: Traceability-Guided Incremental RTL Generation under Requirement Evolution},
author = {Luanrong Chen and Renzhi Chen and Xinyu Li and Shanshan Li and Rui Gong and Lei Wang},
journal= {arXiv preprint arXiv:2603.25769},
year = {2026}
}