审计脚手架而非模型检查点：递归自我改进的平稳性二分法
Audit the Scaffold, Not the Checkpoint: A Stationarity Dichotomy for Recursive Self-Improvement in Agentic Coding
AI 导读
一篇 arXiv 论文提出，审计 AI 编码智能体不能只看模型权重是否重训，还应跟踪其脚手架（工具、测试、任务分解）的改动，因为脚手架改写可在模型不变时扩大可达变更集合。论文提出但未运行相应实验，并区分了固定设置下加搜索、使用中重训和改写脚手架三种情形。测试显示来自同一模型家族的 30 个智能体共败于同一任务，42%（23/55）任务多数失败；多智能体投票只有在失败分布不同时才可能提升上限。
正文 · 原文
Abstract:Rules for AI self-improvement often key on the model itself: has it been retrained, or are its weights frozen? We argue that, for AI coding agents, this check is incomplete, and we propose, but do not run, the experiment that would test it. An agent that keeps revising its own work runs into diminishing returns as long as the set of changes it can reach stays fixed, and can escape them only if that set grows. Our hypothesis is that the set can grow with the model untouched, because the software around the model, its scaffold of tools, tests and task breakdown, can be rewritten. If so, a frozen model guarantees a ceiling eventually but not steady behavior on the way there, and audits should track changes to the scaffold, not only to the model. The same criterion separates three things often lumped together: more search within a fixed setup, retraining the model during use (which can raise the ceiling), and rewriting the scaffold, which sits between them. Adding more agents does not lift the ceiling. Picking the best of several agents' answers reaches the best single agent's ceiling exactly, and only gets there faster. A majority vote could do better, but only if the agents fail on different tasks. In our tests, 30 agents from one model family failed together: some task defeated all of them, and a majority failed 23/55 (42%) of tasks. Our evidence is descriptive. On a public coding benchmark, the gain from each extra round of revision shrinks toward zero, though the unsolved tasks left to measure are also fewer and harder. Across 401 development sessions, the amount of code changed falls off from commit to commit, but programmers working before AI tools show the same pattern, so the data show that current practice levels off without showing why. We reach the criterion by treating repeated revision as a known machine-learning method, boosting, and note where real agents depart from it.
| Comments: | 10 pages main text, 47 pages total, 9 figures, 5 tables |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Software Engineering (cs.SE) |
| MSC classes: | 68T05, 68Q32, 68N30 |
| ACM classes: | I.2.6; I.2.2; D.2.5 |
| Cite as: | arXiv:2609.34924 [cs.LG] |
| (or arXiv:2609.34924v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.34924 arXiv-issued DOI via DataCite |
Submission history
From: Sebastian Bobadilla-Suarez [view email]
[v1]
Mon, 28 Sep 2026 11:25:52 UTC (178 KB)
[v2]
Thu, 12 Nov 2026 12:58:34 UTC (178 KB)
来源：arXiv cs.AI · arxiv.org