超级智能软件工程：随能力扩展的治理机制

View PDF HTML (experimental)

Abstract: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, archived on Zenodo under DOI https://doi.org/10.5281/zenodo.23436020 as a plugin for Claude Code. In OSTEON, 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.

Comments:	16 pages, 6 figures, 6 tables. This version updates citations, corrects a cost figure, marks opinion sentences and clarifies where capability enters the model. Collection scripts and dataset are provided as ancillary files. The OSTEON artifact is archived at this https URL and registrations for the empirical follow-up are at this https URL and this https URL
Subjects:	Software Engineering (cs.SE); Artificial Intelligence (cs.AI)
ACM classes:	D.2.9; D.2.7; I.2.2
Cite as:	arXiv:2610.31306 [cs.SE]
	(or arXiv:2610.31306v2 [cs.SE] for this version)
	https://doi.org/10.48550/arXiv.2610.31306 arXiv-issued DOI via DataCite

Submission history

From: Mohammad Mehdi Gholinejad [view email]
[v1] Thu, 22 Oct 2026 14:04:13 UTC (240 KB)
[v2] Thu, 29 Oct 2026 23:19:56 UTC (240 KB)