Definition
Plain language
A tiny model architecture for solving puzzles through recursive refinement.
As stated in the literature
Tiny Recursive Reasoner — a small (around 7M parameter) recurrent architecture for structured reasoning tasks such as Sudoku-Extreme and grid mazes, prior art for attractor-style models.
Why it matters: It is evidence that for some structured reasoning tasks, recursion and refinement can substitute for sheer model size.
For example, TRM can solve hard Sudoku puzzles with just a few million parameters by iterating its small core network many times.
Heard on the show
“There's a line of work on tiny recursive reasoners — HRM, TRM — that hit really impressive scores on tasks like Sudoku and maze-solving with just a few million parameters.”Episode 041 — When the Iteration Teaches the Model to Skip the Iteration