Quotient Recurrent Reasoner hits 97.9% on Sudoku-Extreme with 78% fewer loops
orvieto_antonio · x · 2026-10-15
Researchers introduced the Quotient Recurrent Reasoner (QRR): symmetry-generated rotations persist while task-relevant dynamics converge faster in quotient space, allowing reasoning to finish while latent states keep moving. It reaches 97.9% on Sudoku-Extreme with 78% fewer loops than FPRM.
More from Research
- SpliceAI2 benchmarks show major gains across nine splicing-variant evaluations — anshulkundaje · 2026-10-16
- GRPO post-training collapses model distributions, clashing with long-horizon agents — zsakib_ · 2026-10-16
- RFdiffusion3 update in Science shows major gains in protease and metallohydrolase design — anshulkundaje · 2026-10-16
- ORL pushes diffusion LMs to a new speed-intelligence Pareto frontier with ~6.9x throughput gains — james_y_zou · 2026-10-16
- Why CoT is the key: classic paper shows transformers need it for serial problems — willcb · 2026-10-16
- Terence Tao: OpenAI's 300-paper dump wiped out junior research projects overnight — Hesamation · 2026-10-16