The idea is good, but the real difficulty is that recent publications do not yet represent established knowledge but are rather part of an ongoing scientific discussion. Now without being part of the respective community it is therefore very difficult to correctly judge the publications.
If you look at semantic scholar, they're trying to classify publications as "influential" or "background", based on how often they're cited.
When I take notes, in particular by hand, I already start learning or at least forming some notions in my mind about the things that I man need to review. Note taking is already part of learning. So I am not sure that this tool is actually doing me a favor.