Metraipolis › archive › dc_996ccdaed4f3

Will AI mess my RTL? A snapshot-based approach to verifying AI-written RTL — arXiv:2611.12712

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.12712
License (as archived)
CC0-1.0
Archived
2026-11-10T18:46:18.803Z
SHA-256 of the archived text
592c716f218b1233eb4e7ac9514b13f4d19187a0d57b9eec5652e5e664703e96
Stable URL of this page
https://metraipolis.com/documento/dc_996ccdaed4f3

How to cite

Will AI mess my RTL? A snapshot-based approach to verifying AI-written RTL — arXiv:2611.12712 — arXiv (en), https://arxiv.org/abs/2611.12712 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_996ccdaed4f3 (Metraipolis archive dc_996ccdaed4f3, sha256 592c716f218b1233eb4e7ac9514b13f4d19187a0d57b9eec5652e5e664703e96)
BibTeX
@misc{dc996ccdaed4f3,
  title = {Will AI mess my RTL? A snapshot-based approach to verifying AI-written RTL — arXiv:2611.12712},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.12712},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_996ccdaed4f3; sha256 592c716f218b1233eb4e7ac9514b13f4d19187a0d57b9eec5652e5e664703e96},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12712. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

With the growing interest in using AI (Artificial Intelligence) for RTL (Register-Transfer Level) hardware development, robust and comprehensive verification has become more important than ever. As Large Language Models (LLMs) increasingly assist in creating and modifying RTL designs, ensuring that these changes preserve existing functionality is paramount for building trust in AI-driven workflows. We present SVApshot, a fully automated framework that leverages LLMs to generate and systematically attempt to correct SystemVerilog Assertions (SVA) for RTL modules, completely removing the human from the generation loop. SVApshot introduces a novel snapshot methodology that captures the current functionality of a design as a comprehensive set of formal assertions, creating a regression suite for validating future changes--whether made by humans or AI. The framework features automated duplicate detection, assertion set expansion, and iterative repair of failing assertions using LLM-guided debugging with formal verification feedback. Our experimental evaluation across diverse RTL modules demonstrates high coverage for complex modules, with successful detection of both manually-injected and AI-introduced bugs. Additionally, this framework opens the door for automatic generation of formal testbenches to benchmark LLMs for hardware design, moving beyond binary pass/fail metrics towards nuanced assertion-based scoring.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.AR, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE) ; Hardware Architecture (cs.AR).
Pagina del lavoro: https://arxiv.org/abs/2611.12712 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-10T18:38:22.454Z dalla pagina https://arxiv.org/list/cs.AR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).