Group Relative Policy Optimization

Follow this topic Ask about this topic

Recent momentum

-15%

22 papers in the last 28 days · 0.4% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

6 new papers

A weekly snapshot of new work published in Group Relative Policy Optimization.

Period ending 2026-09-07

12 new papers

A weekly snapshot of new work published in Group Relative Policy Optimization.

287 papers

Latest in Group Relative Policy Optimization

Browse all topics →

FBOS-RL: Feedback-Driven Bi-Objective Synergistic Reinforcement Learning
May 18, 2026Xikai Zhang, Yongzhi Li, Likang Xiao +6Group Relative Policy Optimization Efficient Exploration
PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
May 18, 2026Wonjoong Kim, Yeonjun In, Sangwu Park +2Group Relative Policy Optimization External Reward Models
GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents
May 18, 2026Xiongbin Wu, Zhihao Luo, Shanzhe Lei +7Group Relative Policy Optimization
Curriculum Group Policy Optimization: Adaptive Sampling for Unleashing the Potential of Text-to-Image Generation
May 18, 2026Baoteng Li, Xianghao Zang, Xinran Wang +8Group Relative Policy Optimization Adaptive Sampling
How Off-Policy Can GRPO Be? Mu-GRPO for Efficient LLM Reinforcement Learning
May 17, 2026Minghao Tian, Yunfei Xie, Chen WeiGroup Relative Policy Optimization Flow-Grpo
Self-Supervised On-Policy Distillation for Reasoning Language Models
May 17, 2026Zhiquan Tan, Yinrong HongUnsupervised On-Policy Self-Distillation On-Policy Distillation
Leveraging Error Diversity in Group Rollouts for Reinforcement Learning
May 17, 2026Wenpu Liu, Yuqi Xu, Weichu Xie +8Reinforcement Learning With Verifiable Reward Long Rollouts
DISA: Offline Importance Sampling for Distribution-Matching LLM-RL
May 17, 2026Shaobo Wang, Yujie Chen, Yafeng Sun +9Importance Sampling Distributional Learning
Latent Action Control for Reasoning-Guided Unified Image Generation
May 16, 2026Fuxiang Zhai, Sixiang Chen, Yingjin Li +4Image Generation Latent Actions
DEVIS-GRPO: Unleashing GRPO on Dynamic Extreme View Synthesis
May 16, 2026Yi Zuo, Huimin Wu, Lingling Li +3Controllable Video Generation Camera Control
Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models
May 16, 2026Siqi Luo, Jianghan Shen, Yi Xin +9Hierarchical Reinforcement Learning Group Relative Policy Optimization
Learn Where Outcomes Diverge: Efficient VLA RL via Probabilistic Chunk Masking
May 15, 2026Vaidehi Bagaria, Nikshep Grampurohit, Pulkit VermaGroup Relative Policy Optimization Reinforcement Learning With Verifiable Reward
Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization
May 15, 2026Xiaoxuan He, Siming Fu, Zeyue Xue +9Pre-Trained Video Diffusion Models Group Relative Policy Optimization
Embedding-perturbed Exploration Preference Optimization for Flow Models
May 15, 2026Sujie Hu, Chubin Chen, Jiashu Zhu +3Group Relative Policy Optimization Perturbations
Interaction-Aware Influence Functions for Group Attribution
May 15, 2026Jaeseung Heo, Kyeongheung Yun, Youngbin Choi +3Efficient Influence Function Influence
VSPO: Vector-Steered Policy Optimization for Behavioral Control
May 15, 2026Xuechen Zhang, Zijian Huang, Kai Yang +3Group Relative Policy Optimization Sparse Rewards
ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both
May 14, 2026Ziyu Guo, Rain Liu, Xinyan Chen +1Latent Visual Reasoning Visual Reasoning
RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO
May 14, 2026Yanzuo Lu, Ronglai Zuo, Jiankang DengAutoregressive Video Diffusion Autoregressive Video Generation
Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax
May 14, 2026Zeli Su, Ziyin Zhang, Zhou Liu +7Group Relative Policy Optimization Deep Reinforcement Learning
KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration
May 14, 2026Ruicheng Zhang, Kaixi Cong, Jun Zhou +5Autoregressive Video Generation Group Relative Policy Optimization
GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models
May 13, 2026Mingzhe Huang, Weijun Wang, Xin Ding +7Visual Token Pruning Large Vision Language Models
GAGPO: Generalized Advantage Grouped Policy Optimization
May 13, 2026Siyuan Zhu, Chao Yu, Rongxin Yang +4Agentic Reinforcement-Learning Framework Group Relative Policy Optimization
F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking
May 13, 2026Rohan Surana, Gagan Mundada, Junda Wu +9Reranking Group Relative Policy Optimization
Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective
May 13, 2026Feng Zhang, Xinhong Ma, Ziqiang Dong +5Group Relative Policy Optimization Reinforcement Learning With Verifiable Reward
Driving Intents Amplify Planning-Oriented Reinforcement Learning
May 12, 2026Hengtong Lu, Victor Shea-Jay Huang, Chengmin Yang +4Group Relative Policy Optimization Vision-Language-Action Models
AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward
May 12, 2026Runhui Huang, Jie Wu, Rui Yang +2Multimodal Generation Unified Multimodal Models
Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
May 12, 2026Yuanda Xu, Hejian Sang, Zhengze Zhou +3Token-Level Supervision On-Policy Distillation
Not How Many, But Which: Parameter Placement in Low-Rank Adaptation
May 12, 2026Arijit Sehanobish, Charles LoveringLow-Rank Adaptation Adapters Gradient Concentration
Holder Policy Optimisation
May 12, 2026Yuxiang Chen, Dingli Liang, Yihang Chen +8Group Relative Policy Optimization Gradient Concentration
Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization
May 12, 2026Xu Chu, Guanyu Wang, Zhijie Tan +4Order Matters Large Language Model Bias
GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation
May 12, 2026Sijia Li, Yuchen Huang, Zifan Liu +7Credit Assignment Group Relative Policy Optimization
Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage Reweighting
May 12, 2026Cheng Wang, Qin Liu, Wenxuan Zhou +1Group Relative Policy Optimization Reasoning Benchmark
Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning
May 12, 2026Swapnil Parekh, Naman GoyalChain-of-Thought Reasoning Explanation Faithfulness
Breaking $\textit{Winner-Takes-All}$ : Cooperative Policy Optimization Improves Diverse LLM Reasoning
May 12, 2026Haoxuan Chen, Tianming Liang, Wei-Shi Zheng +1Large Language Model Reasoning Reinforcement Learning With Verifiable Reward
fg-expo: Frontier-guided exploration-prioritized policy optimization via adaptive kl and gaussian curriculum
May 12, 2026Mingxiong Lin, Zhangquan Gong, Maowen Tang +6Group Relative Policy Optimization Reinforcement Learning With Verifiable Reward
Newton's Lantern: A Reinforcement Learning Framework for Finetuning AC Power Flow Warm Start Models
May 11, 2026Shourya Bose, Helgi Hilmarsson, Dhruv SuriAc Optimal Power Flow Newton
Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping
May 11, 2026Haoyuan Sun, Jing Wang, Yuxin Song +9Text-To-Image Reinforcement Learning Post-Training
RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards
May 11, 2026Gaotang Li, Bhavana Dalvi Mishra, Zifeng Wang +9Rubric-Based Reinforcement Learning Rubrics
DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization
May 11, 2026Mengyi Deng, Zhiwei Li, Xin Li +4Direct Preference Optimization Group Relative Policy Optimization
Relative Score Policy Optimization for Diffusion Language Models
May 11, 2026Zichao Yu, Shengze Xu, Bingqing Jiang +2Reinforcement Learning With Verifiable Reward Diffusion Language Models
StreamPro: From Reactive Perception to Proactive Decision-Making in Streaming Video
May 11, 2026Ao Li, Zihan Xiao, Zihao Yue +7Streaming Video Proactive
expo: Exploration-prioritized policy optimization via adaptive kl regulation and gaussian curriculum sampling
May 11, 2026Mingxiong Lin, Zhangquan Gong, Maowen Tang +6Group Relative Policy Optimization Reinforcement Learning With Verifiable Reward
CoDistill-GRPO: A Co-Distillation Recipe for Efficient Group Relative Policy Optimization
May 9, 2026Soo Min Kwon, Ziteng Sun, Ananda Theertha Suresh +2Group Relative Policy Optimization Flow-Grpo
Flow-OPD: On-Policy Distillation for Flow Matching Models
May 8, 2026Zhen Fang, Wenxuan Huang, Yu Zeng +8Hierarchical Flow Matching Video-Text Alignment
Beyond Pairs: Your Language Model is Secretly Optimizing a Preference Graph
May 8, 2026Ning Liu, Chuanneng Sun, Kristina Klinkner +1Direct Preference Optimization Pairwise Preferences
Interactive Critique-Revision Training for Reliable Structured LLM Generation
May 8, 2026Fei Xu Yu, Zuyuan Zhang, Mahdi Imani +2Verifier Group Relative Policy Optimization
Gradient Starvation in Binary-Reward GRPO: Why Group-Mean Centering Fails and Why the Simplest Fix Works
May 8, 2026Wenhua Nie, Jianan Wu, Junlin Liu +6Group Relative Policy Optimization Group
Gradient-Based LoRA Rank Allocation Under GRPO: An Empirical Study
May 8, 2026Yash Ganpat SawantGradient-Free Rank Allocator Group Relative Policy Optimization
Signal Reshaping for GRPO in Weak-Feedback Agentic Code Repair
May 8, 2026Jia Li, Yuxin Su, Ting Peng +3Potential-Based Reward Shaping Agentic Reinforcement-Learning Framework
Structured Role-Aware Policy Optimization for Multimodal Reasoning
May 8, 2026Bingqing Jiang, Difan ZouMultimodal Reasoning Latent Visual Reasoning
Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models
May 8, 2026Xiaoze Liu, Dhananjay Ram, Yuting Zhang +3Reinforcement Learning Post-Training Group Relative Policy Optimization
Where to Spend Rollouts: Hit-Utility Optimal Rollout Allocation for Group-Based RLVR
May 8, 2026Tao Wang, Shuo Li, Yan Sun +2Group Relative Policy Optimization Reinforcement Learning With Verifiable Reward
DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models
May 8, 2026Amin Karimi Monsefi, Dominic Culver, Nikhil Bhendawade +4Diffusion Language Models Credit Assignment
Gradient Extrapolation-Based Policy Optimization
May 7, 2026Ismam Nur Swapnil, Aranya Saha, Tanvir Ahmed Khan +2Group Relative Policy Optimization Multi-Objective Policy Optimization
A Unified Pair-GRPO Family: From Implicit to Explicit Preference Constraints for Stable and General RL Alignment
May 7, 2026Hao YuTraining-Free Reward Alignment Group Relative Policy Optimization
Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex
May 7, 2026Yun Qu, Qi Wang, Yixiu Mao +11Group Relative Policy Optimization Reinforcement Learning With Verifiable Reward
Beyond Uniform Credit Assignment: Selective Eligibility Traces for RLVR
May 7, 2026Chaoli Mou, Zhan Zhuang, Xinning Chen +1Reinforcement Learning With Verifiable Reward Group Relative Policy Optimization
AGPO: Asymmetric Group Policy Optimization for Verifiable Reasoning and Search Ads Relevance at JD
May 7, 2026Yang Xu, Kun Yao, Yiming Deng +3Reinforcement Learning With Verifiable Reward Group Relative Policy Optimization
Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL
May 7, 2026Zhiyuan Zhai, Xin WangGroup Relative Policy Optimization Long Rollouts
Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration
May 7, 2026Langlin Huang, Chengsong Huang, Jinyuan Li +3Large Language Model Reasoning Reinforcement Learning With Verifiable Reward

May 18, 2026 · cs.LGJ/K move · Enter open · S save

FBOS-RL: Feedback-Driven Bi-Objective Synergistic Reinforcement Learning

Xikai Zhang, Yongzhi Li, Likang Xiao, Yingze Zhang+5

Hangzhou International Innovation Institute, Beihang University · Kuaishou Technology · School of Artificial Intelligence, Beihang University

Reinforcement learning has become a cornerstone for aligning and unlocking the reasoning capabilities of large-scale models. At its core, the training loop of GRPO and its variants alternates between rollout sampling and policy update: the policy first samples rollouts from its action space, and then updates its parameters according to the advantages computed over them. Unlike supervised learning, where each gradient step is anchored to an explicit ground-truth target, the optimal gradient direction for updating model parameters in this setting is not known a priori; the high-quality rollouts drawn during the sampling stage therefore act as the implicit "teacher" that guides every parameter update. However, mainstream RL algorithms such as GRPO adopt a simple sampling scheme that conditions all rollouts on the same original prompt. When a task lies beyond the policy model's current capability, this sampling scheme rarely yields a high-quality rollout, leaving the policy model without a meaningful gradient direction when updating its parameters, which causes training to stall. To address this issue, we propose FBOS-RL. Specifically, we let the model perform Feedback-Guided Exploration Enhancement based on the feedback provided by the environment, and on top of this we design two mutually reinforcing training objectives: EPA and ECC. Extensive experiments demonstrate that EPA and ECC can mutually reinforce each other, forming a positive flywheel effect that significantly improves both the training efficiency and the final performance ceiling of reinforcement learning. Specifically, under both an identical number of rollouts and the same number of training steps, FBOS-RL learns substantially faster than GRPO and feedback-based baselines and ultimately attains a higher performance ceiling, while exhibiting higher policy entropy and lower gradient norms throughout training.

Group Relative Policy Optimization Efficient Exploration

Open paper Ask about it PDF