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.
Alex: Welcome to another episode of ResearchPod.
Sam: Today we're looking at a paper that asks a surprisingly fundamental question about AI research assistants: should they give the same answer to everyone, or should they adapt to the specific scientist using them? The authors argue that a true AI co-scientist has to know who it's working with.
Alex: So the paper is asking whether research help should be tailored to the person, not just the topic?
Sam: Exactly. The problem they identify is that current AI systems can produce research-like output, but they tend to ignore the researcher's own background, tools, and scientific community. And that matters, because a good idea for one scientist might be impossible, obvious, or simply unhelpful for another.
Alex: Why would the same research goal lead to different useful answers?
Sam: Because research isn't just about the question on paper. It also depends on what someone has already done, what methods they know, what data they can access, and who they work with. Those hidden details often determine which directions are actually feasible — and which ones are genuinely new for that particular person.
Alex: So the issue isn't just better automation. It's better fit.
Sam: Right. The authors draw a clear line between a generic research machine and a real collaborator. A generic machine can return a polished output, but a collaborator should return something tuned to the person's strengths, limits, and scientific setting. That's the gap this paper is trying to define.
Alex: How do they want the system to learn that kind of fit?
Sam: They propose building what they call a researcher profile from a research graph. Think of it like a map — where people, papers, journals, institutions, methods, datasets, and topics are all connected by lines showing their relationships. From that map, the system can figure out where a researcher sits in the scientific landscape, not just what papers they've written.
Alex: So it's more than a publication list.
Sam: Much more. A publication list is only a thin snapshot. The graph can also show who someone collaborates with, what communities they're close to, and whether they connect separate areas of science. That last part matters, because the paper suggests a genuinely useful new direction is often not a simple extension of past work — it's a bridge between nearby areas that haven't been linked before.
Alex: And that profile then changes the whole research process?
Sam: That's the core claim. The paper argues that personalization should affect every stage, not just the final response. So the system would use the researcher's context when searching for literature, forming hypotheses, planning experiments, writing, choosing citations, and reviewing the result. It's not a filter applied at the end — it shapes the entire path.
Alex: That sounds broader than the usual assistant tools.
Sam: It is. The authors say existing systems often optimize for the goal alone — they try to make the output look novel or strong in general, but they don't ask whether it's the right kind of output for this particular researcher. Here, the same goal should lead to different research paths for different users.
Alex: But how does the system decide what's actually right for a given person?
Sam: The paper proposes three checks. First, the idea should be achievable with the researcher's real resources and skills. Second, it should fit their scientific identity and community — the kind of work they're known for and the people they work with. Third, it should still bring something new. And the authors are careful to say novelty here doesn't just mean "new to the world." It means new relative to that researcher's own path.
Alex: That makes sense. Otherwise the system could just keep suggesting more of the same.
Sam: Exactly, and the paper flags that as a real failure mode. If two different researchers ask about the same goal, a system that ignores who they are may hand them nearly identical suggestions. That erases the small, personal differences that often lead to original ideas.
Alex: I want to make sure I follow this. If the system already knows the topic, why does the person matter so much?
Sam: Because the topic alone doesn't tell you what can be done next. Two researchers can ask about the same problem, but one might have exactly the right tools, collaborators, and prior work to test a certain approach — while the other simply doesn't. So the same topic can point to very different sensible next steps, depending on who's asking.
Alex: So the paper is really about making the AI act less like a search engine and more like a research partner.
Sam: That's a fair way to put it. And the authors are clear that this is different from the kind of personalization you see in, say, a music recommendation app. There, one answer gets customized. Here, what's being personalized is the entire chain of scientific decisions — the literature search, the hypothesis, the experimental plan, the writing — that eventually produces a research output.
Alex: And how would you even judge whether that works?
Sam: That's something the paper addresses carefully. They argue you shouldn't only ask whether the system can predict the next paper a researcher wrote — because that can reward imitation of history, even when a better idea was available. Instead, they want evaluation that checks whether a suggestion is feasible for that researcher, whether domain experts think it genuinely fits the profile, and whether it leads to better work over time.
Alex: So the big idea isn't just "can AI do research," but "can it do research with the right person in mind."
Sam: That's exactly it. The paper's central point is that personalization isn't a small extra feature you add on top. It's what separates a capable research tool from something that can honestly be called a co-scientist — something that doesn't just know the field, but knows who it's working with.
Alex: Thanks for walking us through it. Thanks for listening to ResearchPod.