Demystifying Reinforcement Learning in Agentic Reasoning
Paper
•
2510.11701
•
Published
•
31
Reinforcement Learning
-
-
LoongRL:Reinforcement Learning for Advanced Reasoning over Long Contexts
Paper • 2510.19363 • Published • 59 -
Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning
Paper • 2510.25992 • Published • 42 -
Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence
Paper • 2511.07384 • Published • 15 -
MarsRL: Advancing Multi-Agent Reasoning System via Reinforcement Learning with Agentic Pipeline Parallelism
Paper • 2511.11373 • Published • 11 -
TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework
Paper • 2511.05385 • Published -
Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance
Paper • 2511.13254 • Published • 121