Less is More: Recursive Reasoning with Tiny Networks
Uses one small network to repeatedly update a reasoning state and a proposed answer. Trains these updates with deep supervision and a learned halting score, evaluating the approach on Sudoku, mazes, and ARC-AGI puzzles.
First public: · Added to this list: November 9, 2026
Explore this approach
Recurrent reasoning — Repeat parts of the model or keep intermediate information in memory while working through a problem. Some methods also learn how many passes to run.