Flow Reasoning Models: Turning Discrete Flows Into Efficient Recurrent Reasoners
Flow Reasoning Models is introduced, a novel framework for structured reasoning that adapts continuous flows over discrete structured outputs with a simple recurrent refinement mechanism by self-conditioning a flow model on its own past outputs, to turn one-shot denoising into iterative solution refinement.
Alec Helbling, Andrey Bryutkin, Mauro Martino et al.
· 0 citations