Rohan Paul@rohanpaul_ai

2026-07-21 05:32· 16小时前

跳到正文

AI 摘要

一篇综述梳理1250篇论文后发现，AI自改进的核心瓶颈在于评估信号的质量。实验表明，模型在无外部检查的10轮自我批评后停止进步，直到加入一个接地步骤才恢复。自改进只有在信号可靠（如证明检查器或测试通过）时才能持续，否则循环会强化错误。

Self-improving AI is only as real as the signal it was tested on to see if it worked.

Sorting 1，250 papers reveals a single bottleneck： the evaluator， who determines what counts as better.

In a controlled experiment， models that were given 10 rounds of self-criticism without any outside check stopped improving until they were given a single grounding step.

So systems get better over time when that signal is strong， like a proof checker or a passing test. When it is weak， like when a model is sure of itself， the loops tend to circle and collapse or reinforce the mistakes the model is most sure of.

People use the term "self-improvement" loosely， as if a model is editing its own draft or an agent is rewriting its own code， obscuring the real differences.

Each method is ranked by what changes in the system， and if each change is still checked by a human.

Each loop is a gamble that we can substitute automatic signals for human judgment， and it improves only when the signal can be trusted.

arxiv. org/abs/2607.07663

Title： "Recursive Self-Improvement in AI： Bounded Self-Refinement to Autonomous Research Loops"

Rohan Paul@rohanpaul_ai · X

41导出 Markdown

2026-07-21 05:32·16小时前

在 X 看原推· x.com

AI 摘要

Self-improving AI is only as real as the signal it was tested on to see if it worked.

Sorting 1，250 papers reveals a single bottleneck： the evaluator， who determines what counts as better.

In a controlled experiment， models that were given 10 rounds of self-criticism without any outside check stopped improving until they were given a single grounding step.

People use the term "self-improvement" loosely， as if a model is editing its own draft or an agent is rewriting its own code， obscuring the real differences.