Metraipolis › archive › dc_ee24448a663f
Spicing up Genetic Netlist Generation with LLMs — arXiv:2608.23317
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.23317
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T07:56:12.916Z
- SHA-256 of the archived text
2f24036775611d702f9d9e685872ef8164c6cdd4fdb737bf023b8034a4127e81- Stable URL of this page
https://metraipolis.com/documento/dc_ee24448a663f
How to cite
Spicing up Genetic Netlist Generation with LLMs — arXiv:2608.23317 — arXiv (en), https://arxiv.org/abs/2608.23317 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ee24448a663f (Metraipolis archive dc_ee24448a663f, sha256 2f24036775611d702f9d9e685872ef8164c6cdd4fdb737bf023b8034a4127e81)
BibTeX
@misc{dcee24448a663f,
title = {Spicing up Genetic Netlist Generation with LLMs — arXiv:2608.23317},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.23317},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ee24448a663f; sha256 2f24036775611d702f9d9e685872ef8164c6cdd4fdb737bf023b8034a4127e81},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23317. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Analog circuit topology synthesis remains challenging because useful designs occupy a tiny fraction of a combinatorial search space, and small structural changes can induce highly nonlinear changes in behavior. Evolutionary algorithms are attractive because they can optimize over discrete circuit topologies using only black-box evaluations, but they often require many SPICE simulations and may converge prematurely. We introduce LLM-SPICEMixer, a hybrid synthesis framework that augments genetic netlist generation with IGEL (Inspiration-Guided Evolution with LLMs), an LLM-based proposal operator. During search, IGEL prompts an LLM with high-performing circuits from the elite set and instructs it to generate a new SPICE netlist, which is then evaluated by SPICE and selected using the same reward mechanism as conventional genetic operators. Thus, the LLM contributes structured topology proposals while simulation remains the source of truth. We evaluate LLM-SPICEMixer on a challenging benchmark task: synthesizing transistor-level circuits that implement a discriminant function for Iris classification. Compared with the genetic framework without LLM guidance, LLM-SPICEMixer improves the median final training reward by 8.4% and the median validation-selected test reward by 8.8%. The best validation-selected circuit achieves 93.3% test accuracy at the nominal tt corner and 85.9% average test accuracy across 17 process, voltage, and temperature corners. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AR). Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Hardware Architecture (cs.AR); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.23317 — 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 2026-10-18T07:48:03.876Z dalla pagina https://arxiv.org/catchup/cs.AR/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).