Mohammad Mehdi Gholinejad · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.31306 · cited by 0 works (OpenAlex) · open-access PDF
Wir definieren superintelligente Software-Engineering als die Disziplin des Aufbaus und der Entwicklung von Software mit Agenten, deren Fähigkeit die der menschlichen Ingenieure übersteigt, in denen Governance (Tore, Verträge, Entscheidungen und Zerfallskontrolle) mit der Fähigkeit schrumpft. Das Argument beruht auf drei Ansprüchen. Erstens beruht die Korrektheit in einem Projekt auf Entscheidungen und Verträgen, die der Code nicht trägt. Zweitens, das Wissen schrumpft. Drittens, sobald ein Agent seine Bewerter übertrifft, fängt das Lesen einen schrumpfenden Anteil der Änderungen auf stalligem Wissen auf. Ein einfaches Modell zeigt, dass eine vergangene Überprüfungskapazität, die Veränderungen in einem Projekt, die
Machine translation (Meta M2M100); the English original follows.
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 (10.5281/zenodo.23436020): 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.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Computer science, Correctness, Corporate governance, Software, Context (archaeology), Software engineering
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31306, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange