Scaling RL to Long Videos
Paper
•
2507.07966
•
Published
•
151
re paper
-
-
Group Sequence Policy Optimization
Paper • 2507.18071 • Published • 252 -
CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning
Paper • 2507.14111 • Published • 19 -
MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge
Paper • 2507.21183 • Published • 10 -
SAND-Math: Using LLMs to Generate Novel, Difficult and Useful Mathematics Questions and Answers
Paper • 2507.20527 • Published • 4 -
Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty
Paper • 2507.16806 • Published • 5 -
EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity
Paper • 2507.21848 • Published • 5 -
Geometric-Mean Policy Optimization
Paper • 2507.20673 • Published • 26 -
A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence
Paper • 2507.21046 • Published • 68 -
L0: Reinforcement Learning to Become General Agents
Paper • 2506.23667 • Published -
Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR
Paper • 2507.15778 • Published • 19 -
SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning
Paper • 2506.19767 • Published • 13 -
R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning
Paper • 2506.04185 • Published -
TreeRPO: Tree Relative Policy Optimization
Paper • 2506.05183 • Published -
TreeRL: LLM Reinforcement Learning with On-Policy Tree Search
Paper • 2506.11902 • Published -
Enhancing Mathematical Reasoning in LLMs by Stepwise Correction
Paper • 2410.12934 • Published • 1 -
ProcessBench: Identifying Process Errors in Mathematical Reasoning
Paper • 2412.06559 • Published • 84