这篇论文用93万条数据告诉你，AI写代码带来的隐患不在单个智能体，而在整个仓库。看完你就明白为什么只测单个AI不够用了。
一篇来自arXiv的论文研究了AI编程智能体在共享仓库中合并拉取请求带来的集成摩擦问题。通过对超过93万条智能体编写的拉取请求进行测量，发现约一半的摩擦变化归因于仓库本身，而非单个贡献或智能体。智能体贡献的仓库级摩擦是人类的约两倍（组内相关系数0.30 vs 0.16），该差距在控制代码库规模、年龄、任务形态等变量后依然存在。论文提出AI原生软件的风险是生态系统属性，应通过仓库级而非单智能体方式进行评估和治理。
Govern the Repository, Not the Agent: Measuring Ecosystem-Level Risk in AI-Native Software
Autonomous coding agents now open and merge pull requests in shared repositories at scale, and the field evaluates them the way it has always evaluated components, one agent at a time, on isolated benchmark tasks. Yet agents that each pass their own tests still leave repositories that accumulate problems no single contribution accounts for. We ask whether this problem belongs to the individual agent or to the repository where it accumulates. We study integration friction, the cost of integrating a contribution into a codebase that other contributors are concurrently changing. Across more than 930,000 agent-authored pull requests, we measure how much of the variation in friction stays with the repository after the contribution, its author, its size, and its agent are accounted for. About half does, and it survives full controls. In the same repositories, agent-authored contributions concentrate this repository-level friction roughly twice as much as human ones (intraclass correlation 0.30 versus 0.16), a gap that holds after controlling for codebase size, age, task shape, process maturity, and merge path. The risk is a property of the ecosystem, not the agent. AI-native software is therefore better measured and governed at the ecosystem level than one agent at a time.