arXiv：cs.AI· Hartwig Grabowski·· 13 小时前
Spec Growth Engine：面向 AI 辅助软件开发、代码耦合的规格增长框架
The Spec Growth Engine: Spec-Anchored, Code-Coupled, Drift-Enforced Architecture for AI-Assisted Software Development
AI 导读
针对 AI 编码智能体的上下文爆炸与规格-代码静默漂移两大失效模式，Spec Growth Engine 提出一种轻量框架。它由机器可读的规格图、将智能体上下文限定在归属路径的 Spine 上下文组装器、强制最难优先的纵向切片增长协议以及将规格-代码分歧设为合并阻断条件的漂移门组成。
正文
Abstract:AI coding agents dramatically accelerate implementation speed but introduce two structural failure modes that existing spec-driven approaches do not fully solve: (1) context explosion -- the agent must reason over an entire repository at once, degrading output quality as the context window fills; and (2) silent spec-code drift -- code evolves, the specification does not, and the divergence becomes invisible until it is costly to repair.
We present the Spec Growth Engine, a lightweight framework that addresses both failure modes through a machine-readable spec graph whose nodes carry explicit contract/design separation, a Spine context assembler that scopes agent context to an ownership path, a vertical-slice growth protocol that enforces hardest-first ordering, and a drift gate that makes spec-code divergence a blocking merge condition.
The design synthesises well-established software engineering principles (Parnas information hiding, C4, ADRs, Walking Skeleton, Reflexion Models, Fitness Functions) into a lean, code-coupled, machine-enforced whole -- without the overhead of heavy-weight frameworks such as RUP or MDA.
| Comments: | 15 pages. Code: this https URL. Implementation: arXiv:2610.11725 |
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.27045 [cs.SE] |
| (or arXiv:2606.27045v2 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2606.27045 arXiv-issued DOI via DataCite |
Submission history
From: Hartwig Grabowski [view email]
[v1]
Thu, 25 Jun 2026 13:51:22 UTC (21 KB)
[v2]
Fri, 9 Oct 2026 16:19:41 UTC (23 KB)
来源：arXiv：cs.AI · arxiv.org