This paper from Tsinghua University and Shanghai Jiao Tong University received perfect scores (6, 6, 6, 6) at NeurIPS 2025! It aims to answer a key question: Does reinforcement learning really make large language models better reasoners? The authors study Reinforcement Learning with Verifiable Rewards (RLVR) and find that while it improves accuracy for small k, it doesn’t create new reasoning patterns—meaning the base model still determines the upper limit of reasoning ability. Across six RLVR variants, performance gains plateau, suggesting that current RL setups mainly refine reasoning rather than reinvent it. Interestingly, it’s distillation, not RL, that shows genuine signs of emergent reasoning. This research points to the next frontier for truly self-improving large language models. Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model? Paper: arxiv.org/abs/2504.13837 Page: limit-of-RLVR.github.io Our report: mp.weixin.qq.com/s/2-GDxs8j1… 📬 #PapersAccepted by Jiqizhixin