Metraipolis › archive › dc_22c687cbc388

SynAct: A Reasoning-Acting Large Language Model Agent for Adaptive Synthesis Optimization — arXiv:2608.12751

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.12751
License (as archived)
CC0-1.0
Archived
2026-10-19T04:18:06.775Z
SHA-256 of the archived text
e4b0b0fe84191ea946d8a07913ba02d34030f09390ed0639ff4bcaca03e07f64
Stable URL of this page
https://metraipolis.com/documento/dc_22c687cbc388

How to cite

SynAct: A Reasoning-Acting Large Language Model Agent for Adaptive Synthesis Optimization — arXiv:2608.12751 — arXiv (en), https://arxiv.org/abs/2608.12751 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_22c687cbc388 (Metraipolis archive dc_22c687cbc388, sha256 e4b0b0fe84191ea946d8a07913ba02d34030f09390ed0639ff4bcaca03e07f64)
BibTeX
@misc{dc22c687cbc388,
  title = {SynAct: A Reasoning-Acting Large Language Model Agent for Adaptive Synthesis Optimization — arXiv:2608.12751},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12751},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_22c687cbc388; sha256 e4b0b0fe84191ea946d8a07913ba02d34030f09390ed0639ff4bcaca03e07f64},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12751. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Logic synthesis transforms RTL designs into gate-level netlists, where PPA results are highly sensitive to the choice of optimization commands, making synthesis tuning both high-dimensional and expensive. Previous approaches fall into two categories: automated methods, which perform black-box search over fixed action spaces with limited decision-level interpretability, and LLM-based methods, which typically generate static scripts upfront and cannot adapt to evolving circuit states. We present SynAct, an adaptive closed-loop LLM reasoning--acting agent that iteratively diagnoses live synthesis reports and reasons over the current circuit state, retrieved tool knowledge, and historical optimization experience to issue targeted commands. SynAct focuses on improving timing, particularly worst negative slack (WNS), while maintaining balanced area and power trade-offs. Experiments on a commercial synthesis tool across 14 designs show that SynAct reduces average WNS to 27% of that from bootstrap synthesis.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI).
Categorie arXiv: Hardware Architecture (cs.AR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.12751 — 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 2026-10-19T04:13:06.698Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).