MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy
Paper
•
2508.05592
•
Published
•
6
Shaoxiong Zhan
Jasaxion
AI & ML interests
None yet
Recent Activity
authored
a paper
2 days ago
RelayFormer: A Unified Local-Global Attention Framework for Scalable
Image and Video Manipulation Localization
authored
a paper
2 days ago
MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging
Synthetic Problems with a Reinforced Policy
Organizations
upvoted
a
paper
2 days ago