IncreRTL: Traceability-Guided Incremental RTL Generation under Requirement Evolution
This work addresses the challenge of requirement evolution in LLM-based RTL generation for engineering deployment, representing an incremental advancement.
The paper tackles the problem of adapting RTL code generation to evolving design requirements by proposing IncreRTL, a framework that uses traceability links to locate and regenerate affected code segments, resulting in improved consistency and efficiency as demonstrated on the EvoRTL-Bench benchmark.
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.