English
Related papers

Related papers: Demystifying Group Relative Policy Optimization: I…

200 papers

Large language model (LLM) alignment via reinforcement learning from human preferences (RLHF) suffers from unstable policy updates, ambiguous gradient directions, poor interpretability, and high gradient variance in mainstream pairwise…

Machine Learning · Computer Science 2026-05-12 Hao Yu

Off-policy reinforcement learning (RL) for large language models (LLMs) is attracting growing interest, driven by practical constraints in real-world applications, the complexity of LLM-RL infrastructure, and the need for further…

Machine Learning · Computer Science 2026-03-03 Chaorui Yao , Yanxi Chen , Yuchang Sun , Yushuo Chen , Wenhao Zhang , Xuchen Pan , Yaliang Li , Bolin Ding

Speech Recognition has seen a dramatic shift towards adopting Large Language Models (LLMs). This shift is partly driven by good scalability properties demonstrated by LLMs, ability to leverage large amounts of labelled, unlabelled speech…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-03 Prashanth Gurunath Shivakumar , Yile Gu , Ankur Gandhe , Ivan Bulyko

Post-training LLMs with Reinforcement Learning, specifically Group Relative Policy Optimization (GRPO), has emerged as a paradigm for enhancing mathematical reasoning. However, standard GRPO relies on scalar correctness rewards that are…

Computation and Language · Computer Science 2026-03-03 Xiwen Chen , Wenhui Zhu , Peijie Qiu , Xuanzhao Dong , Hao Wang , Haiyu Wu , Huayu Li , Aristeidis Sotiras , Yalin Wang , Abolfazl Razi

Reinforcement learning from verifiable rewards has significantly advanced the reasoning capabilities of large language models. However, Group Relative Policy Optimization (GRPO) typically assigns a uniform, sequence-level advantage to all…

Machine Learning · Computer Science 2026-04-06 Song Yu , Li Li , Wenwen Zhao , Zhisheng Yang

On-policy reinforcement learning (RL), particularly Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), has become the dominant paradigm for fine-tuning large language models (LLMs). While policy ratio clipping…

Machine Learning · Computer Science 2026-01-08 Yu Luo , Shuo Han , Yihan Hu , Dong Li , Jianye Hao

Improving and understanding the training dynamics and reasoning of Large Language Models (LLMs) has become essential for their deployment in AI-based security tools, such as software vulnerability detection. In this work, we present an…

Cryptography and Security · Computer Science 2025-07-08 Marco Simoni , Aleksandar Fontana , Giulio Rossolini , Andrea Saracino

Group Relative Policy Optimization (GRPO), which is widely adopted by R1-like reasoning models, has advanced mathematical reasoning. Nevertheless, GRPO faces challenges in reward sparsity, verbosity, and inadequate focus on problem…

Computation and Language · Computer Science 2025-09-23 Jixiao Zhang , Chunsheng Zuo

Recent advances in large language models (LLMs) have shown strong reasoning capabilities through large-scale pretraining and post-training reinforcement learning, demonstrated by DeepSeek-R1. However, current post-training methods, such as…

Artificial Intelligence · Computer Science 2025-12-04 Boyang Gu , Hongjian Zhou , Bradley Max Segal , Jinge Wu , Zeyu Cao , Hantao Zhong , Lei Clifton , Fenglin Liu , David A. Clifton

Group Relative Policy Optimization (GRPO) enhances LLM reasoning but often induces overconfidence, where incorrect responses yield lower perplexity than correct ones, degrading relative calibration as described by the Area Under the Curve…

Machine Learning · Computer Science 2026-04-15 Ziqi Wang , Xingzhou Lou , Meiqi Wu , Zhengqi Wen , Junge Zhang

LLM-based search agents are increasingly trained on entity-centric synthetic data to solve complex, knowledge-intensive tasks. However, prevailing training methods like Group Relative Policy Optimization (GRPO) discard this rich entity…

Computation and Language · Computer Science 2026-02-25 Yida Zhao , Kuan Li , Xixi Wu , Liwen Zhang , Dingchu Zhang , Baixuan Li , Maojia Song , Zhuo Chen , Chenxi Wang , Xinyu Wang , Kewei Tu , Pengjun Xie , Jingren Zhou , Yong Jiang

Recently, GRPO-based reinforcement learning has shown remarkable progress in optimizing flow-matching models, effectively improving their alignment with task-specific rewards. Within these frameworks, the policy update relies on…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Jing Wang , Jiajun Liang , Jie Liu , Henglin Liu , Gongye Liu , Jun Zheng , Wanyuan Pang , Ao Ma , Zhenyu Xie , Xintao Wang , Meng Wang , Pengfei Wan , Xiaodan Liang

Group Relative Policy Optimization (GRPO) significantly enhances the reasoning performance of Large Language Models (LLMs). However, this success heavily relies on expensive external verifiers or human rules. Such dependency not only leads…

Computation and Language · Computer Science 2026-03-03 Nonghai Zhang , Weitao Ma , Zhanyu Ma , Jun Xu , Jiuchong Gao , Jinghua Hao , Renqing He , Jingwen Xu

Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models. While Group Relative Policy Optimization (GRPO) is widely adopted, its coarse credit assignment uniformly…

Machine Learning · Computer Science 2026-04-03 Gengsheng Li , Tianyu Yang , Junfeng Fang , Mingyang Song , Mao Zheng , Haiyun Guo , Dan Zhang , Jinqiao Wang , Tat-Seng Chua

The advantage function is a central concept in RL that helps reduce variance in policy gradient estimates. For language modeling, Group Relative Policy Optimization (GRPO) was proposed to use the within-group sample mean as a baseline for…

Machine Learning · Computer Science 2026-04-23 Hu Wang , Congbo Ma , Ian Reid , Mohammad Yaqub

Image captioning tasks usually use two-stage training to complete model optimization. The first stage uses cross-entropy as the loss function for optimization, and the second stage uses self-critical sequence training (SCST) for…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Xu Liang

Markov Decision Processes are classically solved using Value Iteration and Policy Iteration algorithms. Recent interest in Reinforcement Learning has motivated the study of methods inspired by optimization, such as gradient ascent. Among…

Machine Learning · Computer Science 2021-05-05 Sajad Khodadadian , Prakirt Raj Jhunjhunwala , Sushil Mahavir Varma , Siva Theja Maguluri

Uniform Discrete Diffusion Model (UDM) has recently emerged as a promising paradigm for discrete generative modeling; however, its integration with reinforcement learning remains largely unexplored. We observe that naively applying GRPO to…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Jiaqi Wang , Haoge Deng , Ting Pan , Yang Liu , Chengyuan Wang , Fan Zhang , Yonggang Qi , Xinlong Wang

Reinforcement learning from verifiable rewards has emerged as a powerful technique for enhancing the complex reasoning abilities of Large Language Models (LLMs). However, these methods are fundamentally constrained by the ''learning cliff''…

Computation and Language · Computer Science 2026-03-03 Xichen Zhang , Sitong Wu , Yinghao Zhu , Haoru Tan , Shaozuo Yu , Ziyi He , Jiaya Jia

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