从人类研究决策轨迹中学习科学探索

中文摘要 AI 辅助

构建用于科学研究的AI系统的一个关键挑战是实现科学探索：即通过一系列研究决策和行动来调查未知现象或想法以获取新知识的系统性过程。然而，这一过程在现有的科学语料库中基本缺失；例如，研究论文主要记录最终结果，而非产生这些结果的轨迹。在本工作中，我们引入了ResearchTrails，一个由Git仓库构建的人类研究轨迹数据集，其中提交历史作为研究探索的代理。我们开发了一个自动化且可扩展的流水线，从仓库提交中提取结构化的研究轨迹，捕获方法、实验和消融的连续变化。我们对该数据集进行了特征化，并表明这些轨迹包含了超越最终论文所揭示的关于中间研究决策的有意义信号。我们进一步展示了ResearchTrails在多个用例中的实用性，包括在测试时检索人类研究经验作为外部技能，以及在研究轨迹上训练模型以提高对新研究决策的泛化能力。我们的结果指向了一条路径，使AI系统不仅从科学成果中学习，而且从发现本身的演化过程中学习。

英文摘要

A key challenge in building AI systems for scientific research is enabling $\textit{scientific exploration}$: the systematic process of investigating unknown phenomena or ideas to gain new knowledge through sequences of research decisions and actions. Yet this process is largely missing from existing scientific corpora; for example, research papers primarily record final outcomes rather than the trajectories that produced them. In this work, we introduce $\textbf{ResearchTrails}$, a dataset of $\textbf{human research trajectories constructed from Git repositories}$, where $\textbf{commit histories}$ serve as proxies for research exploration. We develop an automated and scalable pipeline that extracts structured research trajectories from repository commits, capturing successive changes to methods, experiments, and ablations. We characterize the resulting dataset and show that these trajectories contain meaningful signals about intermediate research decisions beyond what final papers reveal. We further demonstrate utilities of ResearchTrails in multiple use cases, including retrieving human research experience as external skills at test time and training models on research trajectories to improve generalization to new research decisions. Our results suggest a path toward AI systems that learn not only from the products of science, but from the evolving process of discovery itself.

发表机构

• University of Chicago（芝加哥大学）

机构由 AI 辅助整理，请以论文原文为准。