Theoretical understanding and optimality of HRM
Establish a formal theoretical understanding of Hierarchical Reasoning Models (HRM) and determine whether their recursive design and training scheme are optimal for supervised reasoning tasks, clarifying the justification for their architecture and potential suboptimality.
References
HRM holds great promise for solving hard problems with small networks, but it is not yet well understood and may be suboptimal.
— Less is More: Recursive Reasoning with Tiny Networks
(Jolicoeur-Martineau, 6 Oct 2025) in Abstract