IncreRTL: Traceability-Guided Incremental RTL Generation under Requirement Evolution
Luanrong Chen, Renzhi Chen, Xinyu Li, Shanshan Li, Rui Gong, Lei Wang

TL;DR
IncreRTL is a framework that uses traceability links to enable incremental RTL code updates driven by large language models, effectively handling evolving requirements and reducing regeneration costs.
Contribution
It introduces a traceability-guided incremental RTL generation approach that improves update accuracy and efficiency under changing design specifications.
Findings
IncreRTL improves regeneration consistency over static methods.
The framework reduces the need for full code regeneration.
Evaluations on EvoRTL-Bench show significant efficiency gains.
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 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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
