Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL Paper • 2602.03773 • Published Feb 3 • 12
QEDBENCH: Quantifying the Alignment Gap in Automated Evaluation of University-Level Mathematical Proofs Paper • 2602.20629 • Published 14 days ago • 3
QEDBENCH: Quantifying the Alignment Gap in Automated Evaluation of University-Level Mathematical Proofs Paper • 2602.20629 • Published 14 days ago • 3
Running on CPU Upgrade Featured 3.04k The Smol Training Playbook 📚 3.04k The secrets to building world-class LLMs
view article Article Kimina-Prover: Applying Test-time RL Search on Large Formal Reasoning Models Jul 10, 2025 • 54