Pinned Loading

1. PRIME-RL/P1PRIME-RL/P1Public

   P1: Mastering Physics Olympiads with Reinforcement Learning

   89 4

2. PRIME-RL/Entropy-Mechanism-of-RLPRIME-RL/Entropy-Mechanism-of-RLPublic

   The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.

   Python 450 15

3. MetaEvo/SymbolMetaEvo/SymbolPublic

   Python implementation of SYMBOL

   Python 18 4

4. MetaEvo/MetaBoxMetaEvo/MetaBoxPublic

   MetaBox: Benchmarking Platform for Meta-Black-Box Optimization

   Python 170 15

5. THUDM/slimeTHUDM/slimePublic

   slime is an LLM post-training framework for RL Scaling.

   Python 8.2k 1.2k

6. verl-project/verlverl-project/verlPublic

   verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

   Python 23.1k 4.4k