Metraipolis › archive › dc_c3674503e13e

The Case for Automated Hyperspecialization: Evidence from SAT — arXiv:2609.14836

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.14836
License (as archived)
CC0-1.0
Archived
2026-10-16T00:31:03.258Z
SHA-256 of the archived text
535f3dde92ff22c0a6636ccdc0e505780422e8c5022467ad89e8f7ac89ce2328
Stable URL of this page
https://metraipolis.com/documento/dc_c3674503e13e

How to cite

The Case for Automated Hyperspecialization: Evidence from SAT — arXiv:2609.14836 — arXiv (en), https://arxiv.org/abs/2609.14836 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c3674503e13e (Metraipolis archive dc_c3674503e13e, sha256 535f3dde92ff22c0a6636ccdc0e505780422e8c5022467ad89e8f7ac89ce2328)
BibTeX
@misc{dcc3674503e13e,
  title = {The Case for Automated Hyperspecialization: Evidence from SAT — arXiv:2609.14836},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14836},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c3674503e13e; sha256 535f3dde92ff22c0a6636ccdc0e505780422e8c5022467ad89e8f7ac89ce2328},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14836. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The software status quo is to use one system to process many different kinds of inputs. In contrast, we propose hyperspecialization: creating new software that is optimized for a single class of inputs. Hyperspecializing manually is anywhere from expensive to impossible. We conjecture that coding agents make automated hyperspecialization cheap, effective, and safe for problems with measurable performance and checkable output. This paper explores one such problem, SAT solving, by synthesizing hundreds of workload-specific SAT solvers at an average cost of \$37 each. Our specialists outperform their competition-winning, general-purpose cousins by 5$\times$ on average, and by over $10\times$ on a quarter of benchmark families. A general-purpose solver constructed from over a hundred of our prototype hyperspecialists won the SAT track at the 2026 SAT Competition.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-15 in cs.SE).
Categorie arXiv: Software Engineering (cs.SE) ; Logic in Computer Science (cs.LO).
Pagina del lavoro: https://arxiv.org/abs/2609.14836 — 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 2026-10-16T00:12:31.102Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).