这篇论文戳中了当前 AI 科学系统的核心瓶颈——只会搜索不会创新，做 AI 科研或科学自动化的团队值得关注，它给出了一个严谨的形式化框架来定义真正的发现。
MIT 新论文提出一种自修正发现系统，旨在让 AI 科学家在科学探索中不仅搜索现有方案，还能识别当前思维框架的局限性并主动引入新概念。现有 AI 科学系统大多在固定设置内搜索，而真实科学需要新变量、工具或假设。该框架通过将数据、模型、失败等所有产出标记为带类型的工件，区分检索、搜索和发现三种操作，其中发现意味着改变系统本身的表达方式。论文试图形式化 AI 系统长期回避的问题：在语言内找到答案与获得改变语言的权利之间的区别。
Great idea for self-evolving AI scientists from th…
Great idea for self-evolving AI scientists from this new MIT paper.
Tries to make an AI scientist notice when its current way of thinking is too small, then add new scientific concepts instead of merely searching harder.
The problem is that most AI science systems still search inside a fixed setup, even when real science sometimes needs new kinds of variables, tools, tests, or claims.
The paper’s core idea is to make every data point, model, tool output, failure, and claim a typed artifact, where typed means the system records what kind of thing it is and how it was produced.
Then the system can tell the difference between retrieval, which adds known things, search, which explores a fixed setup, and discovery, which changes the setup itself.
So novelty AI scientists is not defined by surprise, fluency, or benchmark gain, but by what could not be expressed inside the previous schema.
A serious attempt to formalize something most AI systems still fake: the difference between finding an answer inside a language and earning the right to change the language.
----
arxiv. org/abs/2606.01444
Title: "Self-Revising Discovery Systems for Science: A Categorical Framework for Agentic AI"