Flow Reasoning Models Turn Flow Models Into Recurrent Reasoners, Hitting 99.5% on Sudoku-Extreme
alec_helbling · x · 2026-09-17
Researchers introduce Flow Reasoning Models (FRMs), a structured-reasoning framework that applies continuous flows to discrete structured outputs and recurrently refines predictions via self-conditioning. Unlike autoregressive models that commit sequentially or masked diffusion models needing careful decoding, FRMs make and revise interdependent decisions in parallel, scaling test-time compute by looping longer—each pass gets a local loss, no backprop through time. A new Fixed-Point Forcing (FPF) scheme trains on states from the model's own inference dynamics to fix exposure bias at deeper recurrence. FRMs hit 99.5%, 100.0% and 99.9% solve rates on Sudoku-Extreme, Zebra and Maze-Unique, with higher peak accuracy than masked-diffusion baselines on Sudoku-Extreme.
Related event: Flow Reasoning Models Turn Flow Models into Recurrent Reasoners(3 posts)→
More from Research
- MIT's FloatForm robot boats self-assemble into bridges on water, published in Nature — lukas_m_ziegler · 2026-09-17
- DeepMind open-sources a fruit fly that learned to fly, 59-dim action space on a laptop — anthara_ai · 2026-09-17
- XPeng unveils XPACE, a unified embodied world model powering its IRON humanoid — CyberRobooo · 2026-09-17
- Max-pooling attribution maps model outputs back to input words in new sparse-model release — antoine_chaffin · 2026-09-17
- 99.9% accuracy can mean zero discoveries: the class imbalance trap in scientific ML — bravo_abad · 2026-09-17
- Aeon essay: computism explains our datafied lives — but who tastes the cherries? — round · 2026-09-17