IncreRTL: Traceability-Guided Incremental RTL Generation under Requirement Evolution
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917363458244608 |
|---|---|
| author | Chen, Luanrong Chen, Renzhi Li, Xinyu Li, Shanshan Gong, Rui Wang, Lei |
| author_facet | Chen, Luanrong Chen, Renzhi Li, Xinyu Li, Shanshan Gong, Rui Wang, Lei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_25769 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | IncreRTL: Traceability-Guided Incremental RTL Generation under Requirement Evolution Chen, Luanrong Chen, Renzhi Li, Xinyu Li, Shanshan Gong, Rui Wang, Lei Software Engineering Artificial Intelligence Hardware Architecture 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. |
| title | IncreRTL: Traceability-Guided Incremental RTL Generation under Requirement Evolution |
| topic | Software Engineering Artificial Intelligence Hardware Architecture |
| url | https://arxiv.org/abs/2603.25769 |