Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization
Paper
•
2510.13554
•
Published
•
57
Haoyu Geng
hygeng
·
AI & ML interests
None yet
Recent Activity
liked
a model
about 1 month ago
Qwen/Qwen3-0.6B
upvoted
a
paper
about 2 months ago
Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm
Enables Fine-Grained Policy Optimization
liked
a model
3 months ago
meituan-longcat/LongCat-Flash-Chat
Organizations
None yet