Evolving Deeper LLM Thinking
Paper
•
2501.09891
•
Published
•
115
test-compute
-
-
nvidia/OpenCodeReasoning
Viewer • Updated • 753k • 3.8k • 510 -
nvidia/OpenMathReasoning
Viewer • Updated • 5.68M • 9.01k • 351 -
PrimeIntellect/INTELLECT-2-RL-Dataset
Viewer • Updated • 285k • 152 • 65 -
Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges
Paper • 2508.00454 • Published • 9