Reinforcement Learning with Verifiable Rewards

Also known as RLVR

Overview

This field studies how to improve language and multimodal models by rewarding outputs whose correctness or task progress can be checked, for example with unit tests, mathematical answers, formal proofs, or simulated environments. Common approaches use policy-gradient methods such as PPO and GRPO, with outcome rewards supplemented by step-level feedback, rollout exploration, or replay to improve credit assignment and data efficiency. Work spans math and coding benchmarks as well as search, GUI, and other interactive agents. A central tension is that rewards must be scalable yet faithful: imperfect or narrow verifiers can be exploited, and a correct final answer does not by itself establish sound reasoning, visual grounding, or robust generalization.

Latest papers

CardsList

738 papers69 papers in the last four weeks, down 49% on the four weeks before. 0.5% of all new papers.

  1. Your Group-Relative Advantage Is Biased

    Jan 13, 2026Fengkai Yang, Zherui Chen, Xiaohan Wang +10RL for Language Model ReasoningReinforcement Learning with Verifiable Rewards

  2. GDEPO: Group Dual-dynamic and Equal-right Advantage Policy Optimization for Sample-Efficient Reinforcement Learning

    Jan 11, 2026Zhengqing Yan, Fan Guo, Xinyang Liu +5Group Relative Policy OptimizationReinforcement Learning with Verifiable Rewards

  3. ScalePRM: Training Process Reward Models by Scaling Verification Compute Without Ground Truth

    Dec 2, 2025Salman Rahman, Sruthi Gorantla, Arpit Gupta +3Process Reward ModelsReinforcement Learning with Verifiable Rewards

  4. Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation

    Nov 14, 2025Mohamad Amin Mohamadi, Tianhao Wang, Zhiyuan LiLLM AbstentionLLM Hallucination Mitigation

  5. Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models

    Oct 24, 2025Hoang Phan, Xianjun Yang, Yuanshun Yao +6RL Post-TrainingCatastrophic Forgetting

  6. Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs

    Oct 5, 2025Zishang Jiang, Jinyi Han, Tingyun Li +7RL for Language Model ReasoningLLM-Guided RL

  7. Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers

    Oct 1, 2025Xin-Qiang Cai, Wei Wang, Feng Liu +3Reinforcement LearningRL for Language Model Reasoning

  8. Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners

    Sep 30, 2025Xin Xu, Clive Bai, Kai Yang +4Efficient Language Model ReasoningRL for Language Model Reasoning

  9. Clip-Low Increases Entropy and Clip-High Decreases Entropy in Reinforcement Learning of Large Language Models

    Sep 30, 2025Jaesung R. Park, Junsu Kim, Gyeongman Kim +4Entropy Collapse in RLRL for Language Models

  10. Improving Sampling Efficiency in RLVR through Adaptive Rollout and Response Reuse

    Sep 30, 2025Yuheng Zhang, Wenlin Yao, Changlong Yu +5RL for Language ModelsReinforcement Learning with Verifiable Rewards

  11. Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation

    Sep 8, 2025Ziheng Li, Zexu Sun, Jinman Zhao +8Reinforcement LearningReinforcement Learning with Verifiable Rewards

  12. Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts

    Aug 13, 2025Maxime Heuillet, Yufei Cui, Boxing Chen +2RL for Language Model ReasoningEfficient Language Model Training

  13. Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR

    Jul 21, 2025Runze Liu, Jiakang Wang, Fuzheng Zhang +4RL for Language ModelsRL for Language Model Reasoning

  14. The Invisible Leash: Why RLVR May or May Not Escape Its Origin

    Jul 20, 2025Fang Wu, Weihao Xuan, Danny Xing +5RL for Language Model ReasoningReinforcement Learning with Verifiable Rewards

  15. BNPO: Beta Normalization Policy Optimization

    Jun 3, 2025Changyi Xiao, Mengdi Zhang, Yixin CaoRL for Language Model ReasoningPolicy Gradient Methods

  16. Optimizing Anytime Reasoning via Budget Relative Policy Optimization

    May 19, 2025Penghui Qi, Zichen Liu, Tianyu Pang +3Efficient Language Model ReasoningLLM Reasoning