定义AI原生系统：自主修改自身代码的AI能力
Defining AI-Native Systems: Autonomy as Revision Authority
- 以决策权归属为标准，区分执行者与修改者
- 提出自调优、自重写、自架构三阶升级路径
- 强调自主性但保留人类对目标和正确性的控制
AI已开始编写系统代码：代理可合成、验证并部署系统组件。尽管如此，'AI原生'仍是一个缺乏精确技术定义的营销术语。本文为其提供一个定义。我们沿单一维度——系统自身决策的修订权——来界定AI原生性，而非依赖底层AI模型的能力。基于系统层面的决策模型，我们区分了执行权（谁执行决策）与修订权（谁可修改决策），将修订权组织为阶梯式结构：自调优、自重写、自架构，并定义当AI能自主重写自身实现时，系统即为AI原生。该定义还需包含晋级检测器、验证流程和经验证的回滚机制，同时保持目的和正确性由人类拥有。
原文摘要 · Abstract (English)
AI has begun to write systems code: agents now synthesize, verify, and deploy system components. Despite this shift, "AI-native" remains a marketing term with no precise technical definition. This paper gives it one. We define AI-nativeness along a single axis---authority over the system's own decisions rather than by the capability of the underlying AI models. Building on a decision-level model of a system, we distinguish occupancy (who executes a decision) from revision authority (who may change it), organize revision authority into a ladder---self-tuning, self-rewriting, self-architecting and define a system as AI-native when an AI autonomously rewrites the system's own implementations. The definition further requires an escalation detector, a verification procedure, and a verified fallback, while leaving purpose and correctness human-owned.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。