English
Related papers

Related papers: Smooth Operator: Smooth Verifiable Reward Activate…

200 papers

Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning capabilities of large language models by learning directly from outcome-based rewards. Recent RLVR works that operate under the zero setting…

Machine Learning · Computer Science 2025-10-17 Andrew Zhao , Yiran Wu , Yang Yue , Tong Wu , Quentin Xu , Yang Yue , Matthieu Lin , Shenzhi Wang , Qingyun Wu , Zilong Zheng , Gao Huang

Vision-language models (VLMs) have shown impressive capabilities across diverse tasks, motivating efforts to leverage these models to supervise robot learning. However, when used as evaluators in reinforcement learning (RL), today's…

Robotics · Computer Science 2026-05-27 Philip Schroeder , Thomas Weng , Karl Schmeckpeper , Eric Rosen , Stephen Hart , Ondrej Biza

RL with Verifiable Rewards (RLVR) has emerged as a promising paradigm for improving the reasoning abilities of large language models (LLMs). Current methods rely primarily on policy optimization frameworks like PPO and GRPO, which follow…

Machine Learning · Computer Science 2025-09-30 Haoran He , Yuxiao Ye , Qingpeng Cai , Chen Hu , Binxing Jiao , Daxin Jiang , Ling Pan

Group Relative Policy Optimization (GRPO) has emerged as a popular algorithm for reinforcement learning with large language models (LLMs). However, upon analyzing its clipping mechanism, we argue that it is suboptimal in certain scenarios.…

Machine Learning · Computer Science 2026-01-08 Chi Liu , Xin Chen

Multimodal large language models (MLLMs) have shown promising capabilities in reasoning tasks, yet still struggle with complex problems requiring explicit self-reflection and self-correction, especially compared to their unimodal text-based…

Computation and Language · Computer Science 2025-10-07 Zhongwei Wan , Zhihao Dou , Che Liu , Yu Zhang , Dongfei Cui , Qinjian Zhao , Hui Shen , Jing Xiong , Yi Xin , Yifan Jiang , Chaofan Tao , Yangfan He , Mi Zhang , Shen Yan

Recent advances have shown success in eliciting strong reasoning abilities in multimodal large language models (MLLMs) through rule-based reinforcement learning (RL) with outcome rewards. However, this paradigm typically lacks supervision…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Kaixuan Fan , Kaituo Feng , Haoming Lyu , Dongzhan Zhou , Xiangyu Yue

Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a promising framework for enhancing the reasoning capabilities of large language models. However, existing approaches such as GRPO often suffer from zero gradients. This…

Computation and Language · Computer Science 2025-09-09 Shihui Yang , Chengfeng Dou , Peidong Guo , Kai Lu , Qiang Ju , Fei Deng , Rihui Xin

Reinforcement Learning from Human Feedback (RLHF) plays a crucial role in aligning large language models (LLMs) with human values and preferences. However, the quality and stability of the trained reward model largely determine the final…

Machine Learning · Computer Science 2025-12-17 Chunjin Jian , Xinhua Zhu

While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities across diverse domains, their application to specialized anomaly detection (AD) remains constrained by domain adaptation challenges. Existing Group Relative…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Jingyi Liao , Yongyi Su , Rong-Cheng Tu , Zhao Jin , Wenhao Sun , Yiting Li , Dacheng Tao , Xun Xu , Xulei Yang

We propose Fuzzy Group Relative Policy Reward (FGRPR), a novel framework that integrates Group Relative Policy Optimization (GRPO) with a fuzzy reward function to enhance learning efficiency. Unlike the conventional binary 0/1 accuracy…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Zhiqiang Wang , Pengbin Feng , Yanbin Lin , Shuzhang Cai , Zongao Bian , Jinghua Yan , Xingquan Zhu

Current vision-language models (VLMs) still exhibit inferior performance on knowledge-intensive tasks, primarily due to the challenge of accurately encoding all the associations between visual objects and scenes to their corresponding…

Computation and Language · Computer Science 2024-10-16 Jingyuan Qi , Zhiyang Xu , Rulin Shao , Yang Chen , Jin Di , Yu Cheng , Qifan Wang , Lifu Huang

Reinforcement learning (RL) has become a key driver of language model reasoning. Among RL algorithms, Group Relative Policy Optimization (GRPO) is the de facto standard, avoiding the need for a critic by using per-prompt baselines and…

Machine Learning · Computer Science 2026-02-02 Cheng Ge , Caitlyn Heqi Yin , Hao Liang , Jiawei Zhang

Aligning multimodal generative models with human preferences demands reward signals that respect the compositional, multi-dimensional structure of human judgment. Prevailing RLHF approaches reduce this structure to scalar or pairwise…

Artificial Intelligence · Computer Science 2026-05-12 Juanxi Tian , Fengyuan Liu , Jiaming Han , Yilei Jiang , Yongliang Wu , Yesheng Liu , Haodong Li , Furong Xu , Wanhua Li

Medical visual grounding serves as a crucial foundation for fine-grained multimodal reasoning and interpretable clinical decision support. Despite recent advances in reinforcement learning (RL) for grounding tasks, existing approaches such…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Guangjing Yang , Ziyuan Qin , Chaoran Zhang , Chenlin Du , Jinlin Wang , Wanran Sun , Zhenyu Zhang , Bing Ji , Qicheng Lao

Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for reasoning in language models, with GRPO as its primary example. However, GRPO requires continuous online rollout generation, making it…

Machine Learning · Computer Science 2026-05-21 Richa Verma , Balaraman Ravindran

The application of Vision-Language Models (VLMs) in medicine is critically hampered by the scarcity of high-quality, expert-annotated data. Supervised Fine-Tuning (SFT) on existing datasets often leads to poor generalization on unseen…

Machine Learning · Computer Science 2025-12-09 Weihai Zhi , Jiayan Guo , Shangyang Li

Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning ability of large language models (LLMs), but it often suffers from \textit{restricted exploration}, where the policy rapidly concentrates on a…

Computation and Language · Computer Science 2026-05-13 Hengrui Gu , Xiaotian Han , Yujing Bian , Feiyi Wang , Kaixiong Zhou

We present Stable-Layers, a reinforcement learning framework that eliminates the need for paired supervision by fine-tuning a pretrained layer decomposition model using only feedback from a vision-language model (VLM). Starting from…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Ciara Rowles , Reshinth Adithyan , Nikhil Pinnaparaju , Vikram Voleti , Mark Boss

With respect to improving the reasoning accuracy of LLMs, the representative reinforcement learning (RL) method GRPO faces failure due to insignificant reward variance, while verification methods based on process reward models (PRMs) suffer…

Artificial Intelligence · Computer Science 2025-09-09 Sining Zhoubian , Dan Zhang , Jie Tang

Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks. In realistic reasoning scenarios, LLMs can…