Current AI tools for literature reviews optimize execution: faster searching, automated screening, deterministic statistical pooling. But they skip the step that matters most — thinking.
Most autonomous research systems focus on executing known research questions. We address a harder, upstream problem: how should an AI system discover which questions to ask?
Most executable research artifacts still rely on weak example-based smoke tests. This note proposes self-falsifying skills: methods that ship with small witness suites built from invariants, conservation laws, symmetry checks, and metamorphic relations.