English
Related papers

Related papers: GDEPO: Group Dual-dynamic and Equal-right Advantag…

200 papers

Recent advances in group-based reinforcement learning (RL) have driven frontier large language models (LLMs) in single-turn tasks like mathematical reasoning. However, their scalability to multi-turn LLM agent training remains limited.…

Machine Learning · Computer Science 2025-10-29 Lang Feng , Zhenghai Xue , Tingcong Liu , Bo An

Recent reinforcement learning has enhanced the flow matching models on human preference alignment. While stochastic sampling enables the exploration of denoising directions, existing methods which optimize over multiple denoising steps…

Machine Learning · Computer Science 2026-01-05 Shengjun Zhang , Zhang Zhang , Chensheng Dai , Yueqi Duan

Reinforcement learning (RL) is vital for optimizing large language models (LLMs). Recent Group Relative Policy Optimization (GRPO) estimates advantages using multiple on-policy outputs per prompt, leading to high computational costs and low…

Computation and Language · Computer Science 2025-06-12 Siheng Li , Zhanhui Zhou , Wai Lam , Chao Yang , Chaochao Lu

In an era where tool-augmented AI agents are becoming increasingly vital, our findings highlight the ability of Group Relative Policy Optimization (GRPO) to empower SLMs, which are traditionally constrained in tool use. The ability to use…

Computation and Language · Computer Science 2025-09-10 Dhruvi Paprunia , Vansh Kharidia , Pankti Doshi

Automated theorem proving (ATP) has become an appealing domain for exploring the reasoning ability of the recent successful generative language models. However, current ATP benchmarks mainly focus on symbolic inference, but rarely involve…

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for facilitating the self-improvement of large language models (LLMs), particularly in the domain of complex reasoning tasks. However,…

Machine Learning · Computer Science 2025-07-17 Ziru Liu , Cheng Gong , Xinyu Fu , Yaofang Liu , Ran Chen , Shoubo Hu , Suiyun Zhang , Rui Liu , Qingfu Zhang , Dandan Tu

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

Parallel test-time scaling typically trains separate generation and verification models, incurring high training and inference costs. We propose Advantage Decoupled Preference Optimization (ADPO), a unified reinforcement learning framework…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Xinyu Qiu , Heng Jia , Zhengwen Zeng , Shuheng Shen , Changhua Meng , Yi Yang , Linchao Zhu

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-based reinforcement learning (RL), such as GRPO, has advanced the capabilities of large language models on long-horizon agentic tasks. To enable more fine-grained policy updates, recent research has increasingly shifted toward…

Machine Learning · Computer Science 2026-02-27 Shuo He , Lang Feng , Qi Wei , Xin Cheng , Lei Feng , Bo An

Search agents achieve strong question-answering performance through multi-turn interactions with search engines, with Group Relative Policy Optimization (GRPO) being a widely used training algorithm. However, GRPO-style algorithms still…

Computation and Language · Computer Science 2026-05-28 Jiayi Wu , Ruobing Xie , Zeqian Huang , Lei Jiang , Can Xu , Kangyang Luo , Bochen Lin , Ming Gao , Xiang Li

In this note, we examine the aggregation of preferences achieved by the Group Policy Optimisation (GRPO) algorithm, a reinforcement learning method used to train advanced artificial intelligence models such as DeepSeek-R1-Zero and…

Machine Learning · Computer Science 2025-03-14 Milan Vojnovic , Se-Young Yun

Recent Large Reasoning Models (LRMs) have achieved remarkable performance in solving complex problems via supervised fine-tuning (SFT) and reinforcement learning (RL). Although existing RL algorithms significantly enhance model accuracy,…

Artificial Intelligence · Computer Science 2025-10-20 Zezhong Tan , Hang Gao , Xinhong Ma , Feng Zhang , Ziqiang Dong

Reinforcement learning (RL) plays an increasingly important role in enhancing the reasoning capabilities of large language models (LLMs), yet stable and performant policy optimization remains challenging. Token-level importance ratios often…

Machine Learning · Computer Science 2025-12-02 Chang Gao , Chujie Zheng , Xiong-Hui Chen , Kai Dang , Shixuan Liu , Bowen Yu , An Yang , Shuai Bai , Jingren Zhou , Junyang Lin

Optimizing communication topology is fundamental to the efficiency and effectiveness of Large Language Model (LLM)-based Multi-Agent Systems (MAS). While recent approaches utilize reinforcement learning to dynamically construct…

Computation and Language · Computer Science 2026-03-04 Yueyang Cang , Xiaoteng Zhang , Erlu Zhao , Zehua Ji , Yuhang Liu , Yuchen He , Zhiyuan Ning , Chen Yijun , Wenge Que , Li Shi

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

Standard reinforcement learning from human feedback (RLHF) trains a reward model on pairwise preference data and then uses it for policy optimization. However, while reward models are optimized to capture relative preferences, existing…

Machine Learning · Computer Science 2026-02-05 Kyuseong Choi , Dwaipayan Saha , Woojeong Kim , Anish Agarwal , Raaz Dwivedi

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

Recent advances in large language models (LLMs) have popularized test-time scaling, where models generate additional reasoning tokens before producing final answers. These approaches have demonstrated significant performance improvements on…

Artificial Intelligence · Computer Science 2026-01-13 Wenxun Wu , Yuanyang Li , Guhan Chen , Linyue Wang , Hongyang Chen

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