[论文] Scientist World: Grow a Research World for AI-Scientists

论文概要

研究领域: NLP
作者: Taiming Lu, Sachin Konan, Zhuang Liu
发布时间: 2026-11-05
arXiv: 2611.08478

中文摘要

AI 科学家已经到来，但它们成长的世界还没有。人类科学家将他们的世界视为理所当然——数百年的开放问题和共享思想，等待在科学文献中。对 AI 科学家来说，那个世界可读但不可运行，所以我们为它们构建了 Scientist World：每篇研究论文都变成一个可执行环境。我们的自主流程提取每篇论文的开放式研究问题，并将其提出的方法复现作为基线；进入环境的 AI 科学家将根据人类作者取得的成果进行评估。我们发布了前 1000 个经过验证的环境。以世界作为评估，我们发现前沿 AI 科学家在 74% 的情况下已经能够超越人类研究者。作为 AI 如何做科学的记录，它包含了 6400 小时的研究轨迹，包含每一个想法、实验、失败和成功。作为训练场，我们能够将一个小模型的研究构思能力提高（+158%）以达到与前沿模型相匹配的水平。终于，AI 科学家自己的世界已经到来，从科学中成长，与科学一起成长。

原文摘要

AI-Scientists arrived, but a world for them to grow in did not. Human scientists take theirs for granted \(-\) centuries of open problems and shared ideas, waiting in the scientific literature. To AI-Scientists, that world is readable but not runnable, so we build Scientist World for them: every research paper becomes an executable environment. Our autonomous pipeline extracts each paper's open-ended research question and reproduces its proposed method as the baseline; an AI-Scientist entering the environment is evaluated against what the human authors achieved. We release the first 1,000 verified environments. With the world as an evaluation, we found that frontier AI-Scientists can already surpass the human researchers 74% of the time. As a record of how AI does science, it contains 6,400 ...

自动采集于 2026-11-07

#论文 #arXiv #NLP #小凯