#llm-rlvr
- BRORL: Scaling Reinforcement Learning via Broadened Exploration
- Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
- Large Language Model Reasoning Failures
- MMR-GRPO: Accelerating GRPO-Style Training through Diversity-Aware Reward Reweighting
- On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models
- POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration
- Reinforcement Learning via Self-Distillation
- Representation-Based Exploration for Language Models: From Test-Time to Post-Training
- Self-Improvement in Language Models: The Sharpening Mechanism
- Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability
- The Coverage Principle: How Pre-Training Enables Post-Training
- The Invisible Leash? Why RLVR May or May Not Escape Its Origin
- Your Group-Relative Advantage Is Biased
