How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs Paper • 2606.10646 • Published 2 days ago • 6
Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization Paper • 2510.13554 • Published Oct 15, 2025 • 59