Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Yue et al., 2025, Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model? (arXiv preprint arXiv:2504.13837)
Subscriber deck — free during early access
1 cards in “4.2. Distillation Expands the Reasoning Boundary” · whole deck
4.2. Distillation Expands the Reasoning Boundary
- How does distillation differ from RLVR in Yue et al.’s experiments?DeepSeek-R1-Distill-Qwen-7B, fine-tuned on R1’s long reasoning traces, had a pass@k curve consistently above its base model (Qwen2.5-Math-7B) at all \(k\): distillation brings in new reasoning patterns from a stronger teacher, while RLVR stays within the base model’s limits.
- Yue et al., 2025, Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model? (arXiv preprint arXiv:2504.13837), 4.2. Distillation Expands the Reasoning Boundary
Source
- Yang Yue, Zhiqi Chen, Rui Lu, Andrew Zhao, Zhaokai Wang, Yang Yue, Shiji Song and Gao Huang. 2025. Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?. In arXiv preprint arXiv:2504.13837. https://arxiv.org/abs/2504.13837