English
Related papers

Related papers: Outcome-Grounded Advantage Reshaping for Fine-Grai…

200 papers

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 algorithms such as group-relative policy optimization (GRPO) have shown strong potential for improving the mathematical reasoning capabilities of large language models. While a growing body of work seeks to improve…

Machine Learning · Computer Science 2026-05-12 Wenquan Lu , Hai Huang , Enqi Liu , Randall Balestriero

Group Relative Policy Optimization (GRPO) has become the dominant method for reinforcement learning with verifiable rewards in large language models, but it suffers from two critical limitations: gradient vanishing and diversity collapse.…

Machine Learning · Computer Science 2026-05-20 Khiem Le , Phuc Nguyen , Youssef Mroueh , Chi-Heng Lin , Shangqian Gao , Ting Hua , Nitesh V. Chawla

Reinforcement learning has emerged as a paradigm for post-training large language models, boosting their reasoning capabilities. Such approaches compute an advantage value for each sample, reflecting better or worse performance than…

Computation and Language · Computer Science 2025-12-16 Changpeng Yang , Jinyang Wu , Yuchen Liu , Shuai Zhang , Yang Li , Qiliang Liang , Hongzhen Wang , Shuai Nie , Jiaming Xu , Runyu Shi , Ying Huang , Guoquan Zhang

Recently, Group Relative Policy Optimization (GRPO) has shown promising potential for aligning text-to-image (T2I) models, yet existing GRPO-based methods suffer from two critical limitations. (1) \textit{Shared credit assignment}:…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Qiang Lyu , Zicong Chen , Chongxiao Wang , Haolin Shi , Shibo Gao , Ran Piao , Youwei Zeng , Jianlou Si , Fei Ding , Jing Li , Chun Pong Lau , Weiqiang Wang

Reinforcement learning is emerging as a primary driver for improving language model reasoning capabilities. A fundamental question is whether current reinforcement learning algorithms -- such as Group Relative Policy Optimization (GRPO),…

Machine Learning · Computer Science 2025-06-23 Andre He , Daniel Fried , Sean Welleck

Reinforcement learning from verifiable rewards (RLVR), especially with Group Relative Policy Optimization (GRPO), has shown strong potential for improving the reasoning capabilities of large vision-language models (LVLMs). However, in…

Artificial Intelligence · Computer Science 2026-05-11 Bingqing Jiang , Difan Zou

Enhancing the reasoning capabilities of large language models effectively using reinforcement learning (RL) remains a crucial challenge. Existing approaches primarily adopt two contrasting advantage estimation granularities: token-level…

Machine Learning · Computer Science 2025-10-22 Yiran Guo , Lijie Xu , Jie Liu , Dan Ye , Shuang Qiu

Reasoning abilities, especially those for solving complex math problems, are crucial components of general intelligence. Recent advances by proprietary companies, such as o-series models of OpenAI, have made remarkable progress on reasoning…

Group Relative Policy Optimization (GRPO) has significantly enhanced the reasoning capability of large language models by optimizing the arithmetic mean of token-level rewards. Unfortunately, GRPO is observed to suffer from unstable policy…

Computation and Language · Computer Science 2025-10-21 Yuzhong Zhao , Yue Liu , Junpeng Liu , Jingye Chen , Xun Wu , Yaru Hao , Tengchao Lv , Shaohan Huang , Lei Cui , Qixiang Ye , Fang Wan , Furu Wei

Group Relative Policy Optimization (GRPO) is widely used for critic-free Large Language Model (LLM) post-training, but its KL regularization is usually implemented as a local loss-side token penalty. We show that this misses the…

Machine Learning · Computer Science 2026-05-26 Jiarui Yao , Ruida Wang , Hao Bai , Tong Zhang

We present Future-KL Influenced Policy Optimization (FIPO), a reinforcement learning algorithm designed to overcome reasoning bottlenecks in large language models. While GRPO style training scales effectively, it typically relies on…

Machine Learning · Computer Science 2026-04-01 Chiyu Ma , Shuo Yang , Kexin Huang , Jinda Lu , Haoming Meng , Shangshang Wang , Bolin Ding , Soroush Vosoughi , Guoyin Wang , Jingren Zhou

Reinforcement learning has become the primary paradigm for aligning large language models (LLMs) on complex reasoning tasks, with group relative policy optimization (GRPO) widely used in large-scale post-training. However, GRPO faces…

Machine Learning · Computer Science 2026-01-08 Amir Hossein Yari , Fajri Koto

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

Group-Relative Policy Optimization (GRPO) is a key technique for training large reasoning models, yet it suffers from a critical vulnerability: the \emph{Think-Answer Mismatch}, where noisy reward signals corrupt the learning process. This…

Machine Learning · Computer Science 2025-08-11 Si Shen , Peijun Shen , Wenhua Zhao , Danhao Zhu

Group Relative Policy Optimisation (GRPO) enhances large language models by estimating advantages across a group of sampled trajectories. However, mapping these trajectory-level advantages to policy updates requires aggregating token-level…

Reinforcement learning with verifiable rewards (RLVR) has become a practical route to improve large language model reasoning, and Group Relative Policy Optimization (GRPO) is a widely used optimizer in this setting. However, RLVR training…

Machine Learning · Computer Science 2026-05-14 Tue Le , Linh Ngo Van , Trung Le

The incorporation of online reinforcement learning (RL) into diffusion and flow-based generative models has recently gained attention as a powerful paradigm for aligning model behavior with human preferences. By leveraging stochastic…

Machine Learning · Computer Science 2025-11-25 Yujie Zhou , Pengyang Ling , Jiazi Bu , Yibin Wang , Yuhang Zang , Jiaqi Wang , Li Niu , Guangtao Zhai

The alignment of Large Language Models (LLMs) utilizes Reinforcement Learning from AI Feedback (RLAIF) for non-verifiable domains such as long-form question answering and open-ended instruction following. These domains often rely on LLM…

Machine Learning · Computer Science 2026-05-18 Nirmal Patel , Fei Wang , Inderjit S. Dhillon

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