Search papers, labs, and topics across Lattice.
This paper addresses the limitations of current AI co-scientists by introducing the concept of personalized auto-research, which tailors the research process to individual researchers' contexts and backgrounds. The authors propose a flexible framework that integrates graph-grounded representations of researchers into every stage of the research pipeline, from hypothesis generation to writing and review. Key findings reveal that personalization is essential for fostering genuine collaboration and innovation, as generic outputs often overlook the unique insights and methodologies that individual researchers bring to their work.
Personalization in AI co-scientists could be the key to unlocking novel research insights that generic systems overlook.
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.
