Metraipolis › archive › dc_749293628239

Search-Guided Reasoning Trace Curation for Verilog Generation — arXiv:2610.37706

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.37706
License (as archived)
CC0-1.0
Archived
2026-10-31T06:11:00.970Z
SHA-256 of the archived text
00e1601fc7efca864b144a7a38d2209efba1dd9a7d5fb617c3581d6285e2303e
Stable URL of this page
https://metraipolis.com/documento/dc_749293628239

How to cite

Search-Guided Reasoning Trace Curation for Verilog Generation — arXiv:2610.37706 — arXiv (en), https://arxiv.org/abs/2610.37706 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_749293628239 (Metraipolis archive dc_749293628239, sha256 00e1601fc7efca864b144a7a38d2209efba1dd9a7d5fb617c3581d6285e2303e)
BibTeX
@misc{dc749293628239,
  title = {Search-Guided Reasoning Trace Curation for Verilog Generation — arXiv:2610.37706},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.37706},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_749293628239; sha256 00e1601fc7efca864b144a7a38d2209efba1dd9a7d5fb617c3581d6285e2303e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.37706. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in large language models (LLMs) have improved Verilog generation. However, most training pipelines distill natural-language reasoning traces whose intermediate design decisions are weakly structured and are primarily selected according to the correctness of the final generated RTL. We present MCTS-SFT, a verifier-guided framework for curating reasoning traces for supervised fine-tuning (SFT) of Verilog generation models. MCTS-SFT formulates trace construction as search over intermediate reasoning states and uses Monte Carlo Tree Search (MCTS) to propagate functional feedback from complete Verilog rollouts to earlier design decisions. Within this framework, we introduce Plan-MCTS, which searches over compact hardware-design plans that explicitly represent interfaces, timing, state, behavior, and update rules. We further study plan-preserving supervision, in which the searched structured state is retained as part of the downstream SFT target. Our experiments find that Plan-MCTS achieves the highest functional trace yield, with 84.2% correct traces compared with 81.9% for one-shot structured planning and 82.0% for unguided tree exploration. For identical Plan-MCTS trajectories and Verilog outputs, retaining the explicit searched plan during SFT raises pass@10 from 52.56% to 57.7%, demonstrating that the representation of intermediate design decisions materially affects downstream learning. In a separate 6,000-trace study, MCTS-curated supervision improves pass@10 over full-response chain-of-thought distillation by up to 3.7 points while reducing downstream generation length by approximately 50% on VerilogEval-v2. These results demonstrate that structured hardware planning, verifier-guided search, and explicit intermediate-state supervision provide complementary mechanisms for constructing more effective and token-efficient training data for Verilog generation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Hardware Architecture (cs.AR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.37706 — 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 2026-10-31T06:07:08.587Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).