Skip to main content
Search

# Tiny Recursive Model

2 related articles

Subscribe to updates
  1. arXiv

    Looped refiners swap their per-pass target: multi-answer Sudoku jumps from 2.5% to 98.8%, with no answer list needed

    Looped refiners apply one small network repeatedly to a draft answer, but deep supervision trains every pass toward the single answer the dataset stored; when a puzzle has many correct answers, that target blends them into an invalid grid and leaves a loss floor no model capacity removes. Training each pass instead toward the correct answer nearest its own input, a proximal target, lets the same 1.73M-parameter network solve 98.8% of Sudoku puzzles with 2–64 answers, against 2.5% for the standard target, and 93.8% of sparse puzzles with more than 10,000 answers and no answer list, against 0.0%.

  2. arXiv

    Tiny recursive models drop their two-level state: STRM beats TRM on Sudoku-Extreme at equal compute

    The tiny recursive model TRM relies on a high-level and a low-level state plus nested loops to avoid memorization, which makes its recursion complicated. STRM replaces both states with a single state updated as a bank of fixed-rate, log-spaced exponential moving averages, and reads the answer only from the slowest-updating channels. With the same data, parameters and compute, STRM improves on TRM on Sudoku-Extreme and PPBench, matches it on Maze-Hard, and no longer shows a late drop in held-out accuracy.

You’re all caught up