paper-with-me

홈 › Papers

Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs

2025-06-17 · Xumeng Wen, Zihan Liu, Shun Zheng, Zhijian Xu, Shengyu Ye, Zhirong Wu, Xiao Liang, Yang Wang, Junjie Li, Ziming Miao, Jiang Bian, Mao Yang

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for advancing the reasoning capabilities of Large Language Models (LLMs). However, a critical paradox clouds its efficacy: RLVR-tuned models often underperform their base models on the $Pass@K$ metric for solution-finding, leading to the hypothesis that RLVR merely re-weights existing reasoning paths at the cost of reasoning diversity. In this work, we resolve this contradiction by identifying the source of the problem: the $Pass@K$ metric itself is a flawed measure of reasoning, as it credits correct final answers that probably arise from inaccurate or incomplete chains of thought (CoTs). To address this, we introduce a more precise evaluation metric, $CoT$-$Pass@K$, which mandates that both the reasoning path and the final answer be correct. We provide a new theoretical foundation that formalizes how RLVR, unlike traditional RL, is uniquely structured to incentivize logical integrity. Our empirical results are supportive: using $CoT$-$Pass@K$, we observe that RLVR can incentivize the generalization of correct reasoning for all values of $K$. Furthermore, by analyzing the training dynamics, we find that this enhanced reasoning capability emerges early in the training process and smoothly generalizes. Our work provides a clear perspective on the role of RLVR, offers a more reliable method for its evaluation, and confirms its potential to genuinely advance machine reasoning.

📄 PDF Abstract BibTeX arXiv:2506.14245

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

LongRLVR: Long-Context Reinforcement Learning Requires Verifiable Context Rewards

2026-03-02 · Guanzheng Chen, Michael Qizhe Shieh, Lidong Bing arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capabilities of Large Language Models (LLMs) by optimizing them against factual outcomes. However, this paradigm falters in l…

Reinforcement Learning

ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs

2025-09-22 · Bonan Zhang, Zhongqi Chen, Bowen Song, Qinya Li 외 arxiv

Reinforcement learning (RL) has become a standard paradigm for refining large language models (LLMs) beyond pre-training and instruction tuning. A prominent line of work is RL with verifiable rewards (RLVR), which levera…

Reinforcement Learning

Revisiting LLM Reasoning via Information Bottleneck

2025-07-24 · Shiye Lei, Zhihao Cheng, Kai Jia, Dacheng Tao arxiv

Large language models (LLMs) have recently demonstrated remarkable progress in reasoning capabilities through reinforcement learning with verifiable rewards (RLVR). By leveraging simple rule-based rewards, RL effectively…

Reinforcement LearningMathematical Reasoning

Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains

2025-07-23 · Anisha Gunjal, Anthony Wang, Elaine Lau, Vaskar Nath 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for complex reasoning tasks with clear correctness signals such as math and coding. However, extending it to real-world reasoning tasks is challe…

Reinforcement Learning

Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning

2026-03-10 · Tiehua Mei, Minxuan Lv, Leiyu Pan, Zhenpeng Su 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that arrive at correct answers by chance. …

Reinforcement LearningMathematical Reasoning