Personalized Auto-Research: Towards a True AI Co-Scientist

2026-08-14

AI Summary

This study addresses the limitations of existing AI research systems that overlook individual differences and tend to lose tacit knowledge within generic models. We formally define the task of personalized automated research and propose an end-to-end collaborative framework centered on researcher graph representations. This approach integrates personalization mechanisms throughout the entire workflow, encompassing retrieval, hypothesis generation, experimentation, and writing, alongside a dedicated evaluation system. Beyond enabling precise, individual-centric research support, this work establishes a flexible and generalizable paradigm for personalization. Furthermore, it identifies critical open challenges in the field, thereby laying the theoretical and methodological foundations for next-generation human-AI collaborative scientific discovery.

Abstract

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.

Problem

• Personalized Auto-Research
• AI Co-Scientist
• Researcher-Agnostic
• Tacit Knowledge
• Individual Researcher Context

Innovation

• Personalized Auto-Research
• Graph-grounded Researcher Representations
• AI Co-Scientist
• Full Pipeline Personalization
• Researcher-Agnostic Failure Mode