Recursive Criticality of AI Self-Improvement

• 类型：arxiv
• 标识：2609.00137
• 链接：https://arxiv.org/abs/2609.00137
• 主分类：risk
• 形态：position
• TLDR：AI is increasingly used in the R\&D process that produces future AI systems. We study the conditions under which this feedback becomes self-amplifying. Our model describes how the rate of AI capability growth depends on baseline research productivity, recursive feedback, and the increasing difficulty of research progress. We derive a recursive reproduction number, R_{AI}, that determines whether improvements are amplified or damped across development cycles. This quantity compares the strength of feedback with the rate at which further progress becomes more difficult. When R_{AI}>1, the effect
• 待LLM分类：否
• 标题中文：AI 自我改进的递归临界性
• TLDR中文：AI 正越来越多地用于生产未来 AI 系统的研发流程中。我们研究该反馈在何种条件下会自我放大。我们的模型描述了 AI 能力增长速率如何取决于基线研究生产率、递归反馈以及研究进展难度的递增。我们推导出递归再生数 R_{AI}，用以判断改进在各开发周期中是放大还是衰减。该量比较了反馈强度与后续研究变难的速度。当 R_{AI}>1 时，效果
• 成熟度：research
• 场景：AI self-improvement、feedback loops、capability growth
• 来源文件：
• /inbox/tom/_candidates/2026-09-02-agent-rag-longcontext-candidates.json