Jiahao004/DeepTheorem
Viewer
•
Updated
•
121k
•
306
•
25
DeepTheorem
A dataset and RL-zero pipeline for advanced mathematical reasoning of informal theorem proving.
-
-
Jiahao004/DeepTheorem-qwen-1.5b-rl
2B • Updated • 7 • 1 -
Jiahao004/DeepTheorem-qwen-3b-rl
3B • Updated • 5 -
Jiahao004/DeepTheorem-qwen-7b-rl
8B • Updated • 29 • 3 -
Jiahao004/HMMT_FIMO_Putnam
Updated • 50 • 2 -
DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning
Paper • 2505.23754 • Published • 15