Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models Paper • 2608.16647 • Published 8 days ago • 13
Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models Paper • 2608.16647 • Published 8 days ago • 13
TMAS: Scaling Test-Time Compute via Multi-Agent Synergy Paper • 2605.10344 • Published May 11 • 51
On the Role of Reasoning Patterns in the Generalization Discrepancy of Long Chain-of-Thought Supervised Fine-Tuning Paper • 2604.01702 • Published Apr 4 • 3
On the Role of Reasoning Patterns in the Generalization Discrepancy of Long Chain-of-Thought Supervised Fine-Tuning Paper • 2604.01702 • Published Apr 4 • 3