Following this puts new work involving it at the top of your briefing, with a note saying why it is there. Links are taken from the source record, never inferred.
This is a preprint describing a novel algorithmic framework with theoretical properties and empirical benchmarks, but lacks peer review and addresses a methodological rather than clinical question in machine learning.
A preprint reporting architectural improvements to a multi-objective reinforcement learning algorithm in simulation benchmarks, without peer review, clinical validation, or independent replication.