Metraipolis › archive › dc_958aba050c7d

Superintelligent Software Engineering: Governance That Scales with Capability — arXiv:2610.31306

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.31306
License (as archived)
CC0-1.0
Archived
2026-10-23T15:15:25.749Z
SHA-256 of the archived text
3827f404c6b2e528621e27536fab3755b692047a03bb61638fa18113c756ff13
Stable URL of this page
https://metraipolis.com/documento/dc_958aba050c7d

How to cite

Superintelligent Software Engineering: Governance That Scales with Capability — arXiv:2610.31306 — arXiv (en), https://arxiv.org/abs/2610.31306 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_958aba050c7d (Metraipolis archive dc_958aba050c7d, sha256 3827f404c6b2e528621e27536fab3755b692047a03bb61638fa18113c756ff13)
BibTeX
@misc{dc958aba050c7d,
  title = {Superintelligent Software Engineering: Governance That Scales with Capability — arXiv:2610.31306},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.31306},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_958aba050c7d; sha256 3827f404c6b2e528621e27536fab3755b692047a03bb61638fa18113c756ff13},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31306. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Software agents are being trained to exceed human engineers; we argue that capability alone does not produce better software engineering. We define superintelligent software engineering as the discipline of building and evolving software with agents whose capability exceeds that of human engineers, in which governance (gates, contracts, decisions and decay control) scales with capability. The argument rests on three claims. First, correctness in a project rests on decisions and contracts that the code does not carry. Second, knowledge decays. Third, once an agent outpaces its reviewers, reading catches a shrinking share of the changes built on stale knowledge. A simple model shows that, past a fixed review capacity, escaping changes grow linearly with throughput while the share that reading catches falls toward zero; governance can lower the slope, capability alone cannot. An exploratory snapshot of 452 of the most-starred public GitHub repositories finds a root-level or .github agent context file in 48.67% (95% confidence interval 44.1 to 53.3); in the median file that names repository paths, 9.5% to 22% of those paths do not resolve, depending on how a reference is read. We then present OSTEON, a discipline for the regime, released with a DOI ( https://doi.org/10.5281/zenodo.23436020%29%3A each project gets a governed knowledge repository of decisions and contracts, every change is checked mechanically against it, and the knowledge itself is checked for decay at every session start; planning is gated, and sessions record what they learn without writing rules. We report no measured effect of OSTEON, mark claims about its mechanisms as opinion and the author's practice heuristics as design rationale, and state the questions that would falsify the thesis.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.31306 — 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 2026-10-23T15:09:08.606Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).