Metraipolis › archive › dc_b25c1dade2ef

RTL-Interact: Training EDA-Interactive Models for Multi-Task RTL Design — arXiv:2610.41225

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41225
License (as archived)
CC0-1.0
Archived
2026-11-02T07:38:47.443Z
SHA-256 of the archived text
fc8aca692acb6543dcfa2a3ad8c964e710cedb9ee125911414d5a212d95e8837
Stable URL of this page
https://metraipolis.com/documento/dc_b25c1dade2ef

How to cite

RTL-Interact: Training EDA-Interactive Models for Multi-Task RTL Design — arXiv:2610.41225 — arXiv (en), https://arxiv.org/abs/2610.41225 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b25c1dade2ef (Metraipolis archive dc_b25c1dade2ef, sha256 fc8aca692acb6543dcfa2a3ad8c964e710cedb9ee125911414d5a212d95e8837)
BibTeX
@misc{dcb25c1dade2ef,
  title = {RTL-Interact: Training EDA-Interactive Models for Multi-Task RTL Design — arXiv:2610.41225},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41225},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b25c1dade2ef; sha256 fc8aca692acb6543dcfa2a3ad8c964e710cedb9ee125911414d5a212d95e8837},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41225. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models offer a promising route to register-transfer-level (RTL) design, but reliable implementations require checking and revision based on electronic design automation (EDA) tools' feedback. Existing RTL-specialized models often lack learned interaction with such EDA tools or rely on separate generation and repair components. We introduce RTL-Interact, a multi-task post-training framework that trains a single RTL-specialized model to generate RTL, construct task-appropriate EDA checks, and revise implementations using tool feedback. The framework combines automatically constructed multi-task demonstrations with staged supervision from chain-of-thought to tool-integrated reasoning. We further introduce Pattern-Aware Policy Optimization (PAPO) for multi-task reinforcement learning. PAPO augments Group Relative Policy Optimization with correctness-gated rewards that favor concise successful checking while rewarding effective revision, and uses task grouping to preserve coverage across objectives. On CVDP, RTL-Interact-32B achieves 48.7% weighted Pass@1 and 68.9% Pass@5, surpassing its teacher model, DeepSeek-V3.2, while RTL-Interact-8B achieves 44.9% weighted Pass@1. Additionally, we show that PAPO can reduce average tool calls by 63.8% while improving Pass@1. Both models also outperform all RTL-specialized baselines on VerilogEval v2 and RTLLM v2, demonstrating the effectiveness of our method.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.41225 — 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 2026-11-02T07:37:00.469Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).