Harvard Agentic Science

Find promising research leads

The papers that actually change the direction of your project are almost never in the first page of a Google Scholar search. They are in adjacent fields, written using different terminology, solving what turns out to be the same problem with completely different methods. You cannot search for things you do not know the name of, and that is exactly where the most important leads are.

AI can search by concept instead of by keyword. You describe your research question, what you already know, and where you have already looked. It searches across arXiv, journals, conference proceedings, and neighboring fields for work that connects to yours through shared structure, shared methods, or contradictory findings. It can trace citation chains to find clusters of related work that do not cite each other, which usually means two communities are working on the same problem without knowing it.

You can ask it to cross-reference what it finds: who else is working on related problems, which results disagree with each other, whether there are results from undecipherable pure math papers that apply to your exact problem. The output is a ranked list with enough context per paper to decide in thirty seconds whether it is worth opening.

There are two ways to use AI to find them. Pick the one that fits how you already work.