English
Related papers

Related papers: TreeGRPO: Tree-Advantage GRPO for Online RL Post-T…

200 papers

Reinforcement Learning with Verifiable Rewards (RLVR), particularly with algorithms like Group Relative Policy Optimization (GRPO), has proven highly effective in enhancing the reasoning capabilities of large language models. However, a…

Computation and Language · Computer Science 2026-03-03 Shangyu Xing , Siyuan Wang , Chenyuan Yang , Xinyu Dai , Xiang Ren

Recent advances in reinforcement learning for foundation models, such as Group Relative Policy Optimization (GRPO), have significantly improved the performance of foundation models on reasoning tasks. Notably, the advantage function serves…

Artificial Intelligence · Computer Science 2025-09-26 Wenke Huang , Quan Zhang , Yiyang Fang , Jian Liang , Xuankun Rong , Huanjin Yao , Guancheng Wan , Ke Liang , Wenwen He , Mingjun Li , Leszek Rutkowski , Mang Ye , Bo Du , Dacheng Tao

Process Reinforcement Learning~(PRL) has demonstrated considerable potential in enhancing the reasoning capabilities of Large Language Models~(LLMs). However, introducing additional process reward models incurs substantial computational…

Machine Learning · Computer Science 2025-07-04 Wu Fei , Hao Kong , Shuxian Liang , Yang Lin , Yibo Yang , Jing Tang , Lei Chen , Xiansheng Hua

Stepwise model routing improves the efficiency of Large Reasoning Models (LRMs) by assigning each reasoning step to a suitable model. Recent methods formulate routing as a sequential decision process and train the router with reinforcement…

Artificial Intelligence · Computer Science 2026-05-29 Shenghao Ye , Yu Guo , Zhengheng Li , Shuangwu Chen , Jian Yang

Reinforcement learning methods such as GRPO have seen great popularity in LLM post-training. In GRPO, models produce completions to a set of prompts, which are rewarded, and the policy is updated towards the relatively high reward…

Machine Learning · Computer Science 2026-05-22 Nikolay Blagoev , Oğuzhan Ersoy , Wendelin Boehmer , Lydia Yiyu Chen

RLVR has become a widely adopted paradigm for improving LLMs' reasoning capabilities, and GRPO is one of its most representative algorithms. In this paper, we first show that GRPO admits an equivalent discriminative reformulation as a…

Machine Learning · Computer Science 2026-05-19 Feng Zhang , Xinhong Ma , Ziqiang Dong , Xi Leng , Jianfei Zhao , Xin Sun , Yang Yang , Guanjun Jiang

Recent advancements in reinforcement learning, particularly through Group Relative Policy Optimization (GRPO), have significantly improved multimodal large language models for complex reasoning tasks. However, two critical limitations…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Jisheng Dang , Jingze Wu , Teng Wang , Xuanhui Lin , Nannan Zhu , Hongbo Chen , Wei-Shi Zheng , Meng Wang , Tat-Seng Chua

Post-training methods, especially Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), play an important role in improving large language models' (LLMs) complex reasoning abilities. However, the dominant two-stage pipeline (SFT…

Machine Learning · Computer Science 2025-12-22 Mingyu Su , Jian Guan , Yuxian Gu , Minlie Huang , Hongning Wang

Group Relative Policy Optimization (GRPO) has emerged as a promising critic-free reinforcement learning paradigm for reasoning tasks. However, standard GRPO employs a coarse-grained credit assignment mechanism that propagates group-level…

Computation and Language · Computer Science 2026-01-13 Ziheng Li , Liu Kang , Feng Xiao , Luxi Xing , Qingyi Si , Zhuoran Li , Weikang Gong , Deqing Yang , Yanghua Xiao , Hongcheng Guo

Reinforcement learning (RL) has been successfully applied to autoregressive (AR) and diffusion models. However, extending RL to hybrid AR-diffusion frameworks remains challenging due to interleaved inference and noisy log-probability…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Xiaoxiao Ma , Jiachen Lei , Tianfei Ren , Jie Huang , Siming Fu , Aiming Hao , Jiahong Wu , Xiangxiang Chu , Feng Zhao

Traditional retrieval pipelines optimize utility through stages of candidate retrieval and reranking, where ranking operates over a predefined candidate set. Large Language Models (LLMs) broaden this into a generative process: given a…

Reinforcement learning with verifiable rewards (RLVR), particularly Group Relative Policy Optimization (GRPO), has advanced LLM reasoning. However, GRPO suffers from three credit assignment failures: uniform token-level granularity that…

Machine Learning · Computer Science 2026-05-07 Song Yu , Li Li , Wenwen Zhao , Zhisheng Yang

Aligning large language models (LLMs) with human values and safety constraints is challenging, especially when objectives like helpfulness, truthfulness, and avoidance of harm conflict. Reinforcement Learning from Human Feedback (RLHF) has…

Computation and Language · Computer Science 2025-03-31 Xuying Li , Zhuo Li , Yuji Kosuga , Victor Bian

Group-based reinforcement learning (RL) methods have achieved remarkable success in improving the performance of large language models (LLMs) and have been rapidly extended to agentic tasks. However, their credit assignment relies heavily…

Machine Learning · Computer Science 2026-05-27 Xin Cheng , Shuo He , Lang Feng , HaiYang Xu , Ming Yan , Lei Feng , Bo An

Recent GRPO-based approaches built on flow matching models have shown remarkable improvements in human preference alignment for text-to-image generation. Nevertheless, they still suffer from the sparse reward problem: the terminal reward of…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Haoyou Deng , Keyu Yan , Chaojie Mao , Xiang Wang , Yu Liu , Changxin Gao , Nong Sang

Group Relative Policy Optimization (GRPO) assigns a single scalar advantage to all tokens in a completion. For structured generations with explicit segments and objectives, this couples unrelated reward signals across segments, leading to…

Machine Learning · Computer Science 2026-02-12 Kirill Pavlenko , Alexander Golubev , Simon Karasik , Boris Yangel

Recent advancements in flow-matching have enabled high-quality text-to-image generation. However, the deterministic nature of flow-matching models makes them poorly suited for reinforcement learning, a key tool for improving image quality…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Benjamin Yu , Jackie Liu , Justin Cui

In this work, we aim to incentivize the reasoning ability of Multimodal Large Language Models (MLLMs) via reinforcement learning (RL) and develop an effective approach that mitigates the sparse reward and advantage vanishing issues during…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Huanjin Yao , Qixiang Yin , Jingyi Zhang , Min Yang , Yibo Wang , Wenhao Wu , Fei Su , Li Shen , Minghui Qiu , Dacheng Tao , Jiaxing Huang

Reinforcement learning (RL), earlier proven to be effective in large language and multi-modal models, has been successfully extended to enhance 2D image generation recently. However, applying RL to 3D generation remains largely unexplored…

Computer Vision and Pattern Recognition · Computer Science 2025-12-12 Yiwen Tang , Zoey Guo , Kaixin Zhu , Ray Zhang , Qizhi Chen , Dongzhi Jiang , Junli Liu , Bohan Zeng , Haoming Song , Delin Qu , Tianyi Bai , Dan Xu , Wentao Zhang , Bin Zhao

Group Relative Policy Optimization (GRPO) is highly effective for post-training autoregressive (AR) language models, yet its direct application to diffusion large language models (dLLMs) often triggers reward collapse. We identify two…

Machine Learning · Computer Science 2026-03-10 Jianyuan Zhong , Kaibo Wang , Ding Ding , Zijin Feng , Haoli Bai , Yang Xiang , Jiacheng Sun , Qiang Xu