English
Related papers

Related papers: E-GRPO: High Entropy Steps Drive Effective Reinfor…

200 papers

Reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving reasoning language models on tasks such as mathematics, coding, and scientific question answering. However, widely used group-relative…

Computation and Language · Computer Science 2026-05-29 Redacted by arXiv

Group-based reinforcement learning methods, like Group Relative Policy Optimization (GRPO), are widely used nowadays to post-train large language models. Despite their empirical success, they exhibit structural mismatches between reward…

Machine Learning · Computer Science 2026-01-09 Aleksandar Fontana , Marco Simoni , Giulio Rossolini , Andrea Saracino , Paolo Mori

Group-based reinforcement learning algorithms such as Group Reward Policy Optimization (GRPO) have proven effective for fine-tuning large language models (LLMs) with human feedback. However, generating and storing multiple responses per…

Machine Learning · Computer Science 2025-07-01 Liangyu Wang , Huanyi Xie , Xinhai Wang , Tianjin Huang , Mengdi Li , Di Wang

A significant portion of recent research on Large Language Model (LLM) alignment focuses on developing new policy optimization methods based on Group Relative Policy Optimization (GRPO). Two prominent directions have emerged: (i) a shift…

Machine Learning · Computer Science 2026-02-27 Svetlana Glazyrina , Maksim Kryzhanovskiy , Roman Ischenko

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

Recent Progress in post-training flow matching for text-to-image (T2I) generation with Group Relative Policy Optimization (GRPO) has demonstrated strong potential. However, it is hindered by a critical limitation: inaccurate advantage…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Yifu Luo , Haoyuan Sun , Xinhao Hu , Penghui Du , Keyu Fan , Bo Li , Sinan Du , Xu Wan , Zhiyu Chen , Bo Xia , Tiantian Zhang , Yongzhe Chang , Changqian Yu , Kun Gai , Xueqian Wang

This paper provides a self-contained, from-scratch, exposition of key algorithms for instruction tuning of models: SFT, Rejection Sampling, REINFORCE, Trust Region Policy Optimization (TRPO), Proximal Policy Optimization (PPO), Group…

Computation and Language · Computer Science 2025-10-22 Rohit Patel

This paper introduces two novel modifications to the Dynamic sAmpling Policy Optimization (DAPO) algorithm [1], approached from a mixed-policy perspective. Standard policy gradient methods can suffer from instability and sample…

Machine Learning · Computer Science 2025-08-20 Hongze Tan , Yuchen Li

Discrete flow models (DFMs) are a class of flexible generative models for generating discrete data, and diffusion large language models (dLLMs) can be viewed as a special case with a specific choice of mixture path and a masked source…

Machine Learning · Computer Science 2026-05-12 Zhengyan Wan , Yidong Ouyang , Panwen Hu , Qiang Sun

Streaming autoregressive (AR) video generators combined with few-step distillation achieve low-latency, high-quality synthesis, yet remain difficult to align via reinforcement learning from human feedback (RLHF). Existing SDE-based GRPO…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Dailan He , Guanlin Feng , Xingtong Ge , Yi Zhang , Bingqi Ma , Guanglu Song , Yu Liu , Hongsheng Li

Group Relative Policy Optimization (GRPO) has emerged as a powerful framework for preference alignment in text-to-image (T2I) flow models. However, we observe that the standard paradigm where evaluating a group of generated samples against…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Jiazi Bu , Pengyang Ling , Yujie Zhou , Yibin Wang , Yuhang Zang , Tianyi Wei , Xiaohang Zhan , Jiaqi Wang , Tong Wu , Xingang Pan , Dahua Lin

The remarkable performance of Large Language Models (LLMs) highly relies on crafted prompts. However, manual prompt engineering is a laborious process, creating a core bottleneck for practical application of LLMs. This phenomenon has led to…

Computation and Language · Computer Science 2025-11-21 Qing Zhang , Bing Xu , Xudong Zhang , Yifan Shi , Yang Li , Chen Zhang , Yik Chung Wu , Ngai Wong , Yijie Chen , Hong Dai , Xiansen Chen , Mian Zhang

Group Relative Policy Optimization (GRPO) has significantly advanced the reasoning ability of large language models (LLMs), particularly by boosting their mathematical performance. However, GRPO and related entropy-regularization methods…

Computation and Language · Computer Science 2025-10-13 Xingyu Lin , Yilin Wen , En Wang , Du Su , Wenbin Liu , Chenfu Bao , Zhonghou Lv

We propose Process-Aware Policy Optimization (PAPO), a method that integrates process-level evaluation into Group Relative Policy Optimization (GRPO) through decoupled advantage normalization, to address two limitations of existing reward…

Artificial Intelligence · Computer Science 2026-04-06 Zelin Tan , Zhouliang Yu , Bohan Lin , Zijie Geng , Hejia Geng , Yudong Zhang , Mulei Zhang , Yang Chen , Shuyue Hu , Zhenfei Yin , Chen Zhang , Lei Bai

Software engineering presents complex, multi-step challenges for Large Language Models (LLMs), requiring reasoning over large codebases and coordinated tool use. The difficulty of these tasks is exemplified by benchmarks like SWE-bench,…

Artificial Intelligence · Computer Science 2026-02-05 Jiahao Yu , Zelei Cheng , Xian Wu , Xinyu Xing

Trust Region Policy Optimization (TRPO) is a popular and empirically successful policy search algorithm in reinforcement learning (RL). It iteratively solved the surrogate problem which restricts consecutive policies to be close to each…

Machine Learning · Computer Science 2021-10-27 Sahar Roostaie , Mohammad Mehdi Ebadzadeh

Latent reasoning offers a more efficient alternative to explicit reasoning by compressing intermediate reasoning into continuous representations and substantially shortening reasoning chains. However, existing latent reasoning methods…

Machine Learning · Computer Science 2026-05-01 Jingcheng Deng , Zihao Wei , Liang Pang , Junhong Wu , Shicheng Xu , Zenghao Duan , Huawei Shen

Entropy regularization is an important idea in reinforcement learning, with great success in recent algorithms like Soft Q Network (SQN) and Soft Actor-Critic (SAC1). In this work, we extend this idea into the on-policy realm. We propose…

Machine Learning · Computer Science 2020-10-19 Jingbin Liu , Xinyang Gu , Shuai Liu

We consider a problem of learning the reward and policy from expert examples under unknown dynamics. Our proposed method builds on the framework of generative adversarial networks and introduces the empowerment-regularized maximum-entropy…

Machine Learning · Computer Science 2019-02-26 Ahmed H. Qureshi , Byron Boots , Michael C. Yip

Integrating expressive generative policies, such as flow-matching models, into offline reinforcement learning (RL) allows agents to capture complex, multi-modal behaviors. While Q-learning with Adjoint Matching (QAM) stabilizes policy…

Machine Learning · Computer Science 2026-05-11 Abdelghani Ghanem , Mounir Ghogho