English
Related papers

Related papers: DGPO: Distribution Guided Policy Optimization for …

200 papers

Recent advancements in Large Reasoning Models (LRMs), exemplified by DeepSeek-R1, have underscored the potential of scaling inference-time compute through Group Relative Policy Optimization (GRPO). However, GRPO frequently suffers from…

Artificial Intelligence · Computer Science 2026-02-09 Yu Zhao , Fan Jiang , Tianle Liu , Bo Zeng , Yu Liu , Longyue Wang , Weihua Luo

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

The recent success and openness of DeepSeek-R1 have brought widespread attention to Group Relative Policy Optimization (GRPO) as a reinforcement learning method for large reasoning models (LRMs). In this work, we analyze the GRPO objective…

Machine Learning · Computer Science 2026-01-07 Gang Li , Ming Lin , Tomer Galanti , Zhengzhong Tu , Tianbao Yang

Group Relative Policy Optimization (GRPO) was introduced and used recently for promoting reasoning in LLMs under verifiable (binary) rewards. We show that the mean + variance calibration of these rewards induces a weighted contrastive loss…

Machine Learning · Computer Science 2025-10-22 Youssef Mroueh

Recent progress in Large Language Model (LLM) reasoning is increasingly driven by the refinement of post-training loss functions and alignment strategies. However, standard Reinforcement Learning (RL) paradigms like Group Relative Policy…

Machine Learning · Computer Science 2026-01-28 Kishan Panaganti , Zhenwen Liang , Wenhao Yu , Haitao Mi , Dong Yu

Self-Distillation Policy Optimization (SDPO) provides dense token-level credit assignment for reinforcement learning with large language models by leveraging the model's own feedback-conditioned predictions as a self-teacher. Unlike GRPO,…

Machine Learning · Computer Science 2026-05-28 Zehao Liu , Yuanpu Cao , Jinghui Chen , Vasant G. Honavar

Post-training plays a crucial role in refining and aligning large language models to meet specific tasks and human preferences. While recent advancements in post-training techniques, such as Group Relative Policy Optimization (GRPO),…

Artificial Intelligence · Computer Science 2025-10-28 Kaichen Zhang , Yuzhong Hong , Junwei Bao , Hongfei Jiang , Yang Song , Dingqian Hong , Hui Xiong

Policy optimization for large language models often suffers from sparse reward signals in multi-step reasoning tasks. Critic-free methods like GRPO assign a single normalized outcome reward to all tokens, providing limited guidance for…

Machine Learning · Computer Science 2026-02-04 Ruiyi Ding , Yongxuan Lv , Xianhui Meng , Jiahe Song , Chao Wang , Chen Jiang , Yuan Cheng

Recent advances in reinforcement learning (RL) have achieved great successes by leveraging the multimodality and exploration capability of diffusion policies. Among these approaches, one representative branch focuses on the sampling-based…

Robotics · Computer Science 2026-05-29 Shutong Ding , Zejia Zhong , Zhongyi Wang , Ke Hu , Bikang Pan , Jingya Wang , Ye Shi

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

Large Language Models (LLMs) are increasingly aligned with human preferences through Reinforcement Learning from Human Feedback (RLHF). Among RLHF methods, Group Relative Policy Optimization (GRPO) has gained attention for its simplicity…

Computation and Language · Computer Science 2025-09-25 Yuhang Zhou , Jing Zhu , Shengyi Qian , Zhuokai Zhao , Xiyao Wang , Xiaoyu Liu , Ming Li , Paiheng Xu , Wei Ai , Furong Huang

Existing Reinforcement Learning from Verifiable Rewards (RLVR) methods, such as Group Relative Policy Optimization (GRPO), have achieved remarkable progress in improving the reasoning capabilities of Large Reasoning Models (LRMs). However,…

Machine Learning · Computer Science 2026-04-16 Hsiu-Yuan Huang , Chenming Tang , Weijie Liu , Clive Bai , Saiyong Yang , Yunfang Wu

We present Anchored Direct Preference Optimization (ADPO), a policy alignment method derived from first principles of KL-regularized reinforcement learning. Unlike standard approaches that treat the reference policy merely as a regularizer,…

Machine Learning · Computer Science 2026-01-13 Wang Zixian

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

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

We present Group Orthogonalized Policy Optimization (GOPO), a new alignment algorithm for large language models derived from the geometry of Hilbert function spaces. Instead of optimizing on the probability simplex and inheriting the…

Machine Learning · Computer Science 2026-02-26 Wang Zixian

Group Relative Policy Optimization (GRPO) has emerged as a promising approach for improving the reasoning capabilities of large language models. However, it struggles to effectively balance the tradeoff between exploration and exploitation…

Computation and Language · Computer Science 2026-05-13 Cheng Wang , Qin Liu , Wenxuan Zhou , Muhao Chen

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

Reinforcement Learning (RL) is pivotal for enhancing Large Language Model (LLM) reasoning, yet mainstream algorithms such as GRPO and DAPO remain constrained by a coarse-grained credit assignment paradigm, where all tokens within the same…

Computation and Language · Computer Science 2026-02-06 Hongze Tan , Zihan Wang , Jianfei Pan , Jinghao Lin , Hao Wang , Yifan Wu , Tao Chen , Zhihang Zheng , Zhihao Tang , Haihua Yang

Large Language Models (LLMs) have shown promise in solving complex mathematical problems, yet they still fall short of producing accurate and consistent solutions. Reinforcement Learning (RL) is a framework for aligning these models with…

Artificial Intelligence · Computer Science 2026-02-10 Ali Hatamizadeh , Shrimai Prabhumoye , Igor Gitman , Ximing Lu , Seungju Han , Wei Ping , Yejin Choi , Jan Kautz