Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning
Paper
•
2509.22601
•
Published
•
29
grpo
-
-
Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
Paper • 2509.25849 • Published • 47 -
GEM: A Gym for Agentic LLMs
Paper • 2510.01051 • Published • 88 -
Reinforce-Ada: An Adaptive Sampling Framework for Reinforce-Style LLM Training
Paper • 2510.04996 • Published • 15 -
Training-Free Group Relative Policy Optimization
Paper • 2510.08191 • Published • 44