个性化自动研究：迈向真正的AI合作科学家

摘要

能够生成假设、检索相关工作、设计实验、执行代码并撰写完整论文的AI共同科学家，正开始改变研究的开展方式。尽管进展迅速，最先进的系统仍然与研究者无关：给定一个研究目标，它们优化新颖性、有效性或评审分数，却忽略了将使用输出的具体科学家。这忽视了研究的一个基本事实，即什么算作新颖、有价值或可行，取决于研究者本人，包括其先前工作、方法论储备，以及其所处的合作者与学术共同体。在这项工作中，我们提出了个性化自动研究的问题，该问题要求研究过程的每个阶段都基于对个体研究者的表征来进行条件化。我们认为，个性化不是一个便利性附加层，而是使AI系统能够充当真正的共同科学家而非通用工具的根本属性。为解决这一问题，我们提出一个通用且灵活的框架，将基于图的研究者上下文贯穿于检索、假设搜索、实验、写作和评审之中。该框架包含三个基本组成部分：(i) 基于图的研究者表征；(ii) 整个研究流程中的个性化；(iii) 基于个体研究者本身的评估。值得注意的是，我们强调了一种一刀切的失败模式：不同的研究者提出相同目标时，会收到本质上相同的研究，从而抹除了新想法得以产生的隐性知识。最后，我们讨论了基本的开放问题与挑战。

English

AI co-scientists that generate hypotheses, retrieve related work, design experiments, execute code, and draft full papers are beginning to change how research is carried out. Despite this rapid progress, state-of-the-art systems remain researcher-agnostic: given a research goal, they optimize novelty, validity, or reviewer score while ignoring the individual scientist who will use the output. This overlooks a fundamental fact about research, namely, that what counts as novel, valuable, or feasible depends on the researcher, including their prior work, methodological repertoire, and the collaborators and communities in which they are embedded. In this work, we introduce the problem of personalized auto-research, which conditions every stage of the research process on a representation of the individual researcher. We argue that personalization is not a convenience layer, but rather the fundamental property that allows an AI system to serve as a genuine co-scientist rather than a generic instrument. To address this problem, we propose a general and flexible framework that threads a graph-grounded researcher context through retrieval, hypothesis search, experimentation, writing, and review. The framework consists of three fundamental components: (i) graph-grounded researcher representations, (ii) personalization across the full research pipeline, and (iii) evaluation grounded in the individual. Notably, we highlight a one-size-fits-all failure mode where distinct researchers issuing the same goal receive essentially the same research, erasing the tacit knowledge through which novel ideas arise. Finally, we discuss fundamental open problems and challenges.