Tags
40 个页面
Reasoning
K2-Think：A Parameter-Efficient Reasoning System
Parallel-R1：Towards Parallel Thinking via Reinforcement Learning
Reverse-Engineered Reasoning for Open-Ended Generation
The Majority is not always right：RL training for solution aggregation
Less is More Tokens：Efficient Math Reasoning via Difficulty-Aware Chain-of-Thought Distillation
BEYOND CORRECTNESS：HARMONIZING PROCESS AND OUTCOME REWARDS THROUGH RL TRAINING
Learning to Refine：Self-Refinement of Parallel Reasoning in LLMs
未命名
GHPO：ADAPTIVE GUIDANCE FOR STABLE AND EFFICIENT LLM REINFORCEMENT LEARNING
Understanding Tool-Integrated Reasoning
1
2
3
4
跳转到页码
(1 - 4)
跳转
Enter
按 Enter 键跳转