Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony Paper • 2510.11345 • Published Oct 13, 2025 • 15
Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization Paper • 2510.13554 • Published Oct 15, 2025 • 57
