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 →

Rollout Pass-Rate Control: Steering Binary-Reward RL Toward Its Most Informative Regime
May 6, 2026Tianshu Zhu, Wenyu Zhang, Xiaoying Zuo +8Rollout Group Relative Policy Optimization
EP-GRPO: Entropy-Progress Aligned Group Relative Policy Optimization with Implicit Process Guidance
May 6, 2026Song Yu, Li Li, Wenwen Zhao +1Group Relative Policy Optimization Reinforcement Learning With Verifiable Reward
Maximizing Rollout Informativeness under a Fixed Budget: A Submodular View of Tree Search for Tool-Use Agentic Reinforcement Learning
May 6, 2026Yuelin Hu, Zhenbo Yu, Zhengxue Cheng +2Rollout Agentic Reinforcement-Learning Framework
GRPO-TTA: Test-Time Visual Tuning for Vision-Language Models via GRPO-Driven Reinforcement Learning
May 5, 2026Yujun Li, Hongyuan Zhang, Yuan YuanVision-Language Model Adaptation Group Relative Policy Optimization
Orchestrating Spatial Semantics via a Zone-Graph Paradigm for Intricate Indoor Scene Generation
May 4, 2026Meisheng Zhang, Shizhao Sun, Yang Zhao +3Indoor Scene Generation Group Relative Policy Optimization
Enhanced LLM Reasoning by Optimizing Reward Functions with Search-Driven Reinforcement Learning
May 3, 2026Arash Ahmadi, Sarah Sharif, Yaser +1Large Language Model Reasoning External Reward Models
Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization
May 2, 2026Yunhan Bu, Quan Zhang, Huaping Zhang +9Multi-Hop Reasoning Structural Causal Model
Cost-Aware Learning
Apr 30, 2026Clara Mohri, Amir Globerson, Haim Kaplan +2Group Relative Policy Optimization Stochastic Gradient Descent
Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning
Apr 30, 2026Jingcheng Deng, Zihao Wei, Liang Pang +4Efficient Latent Reasoning Group Relative Policy Optimization
Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO
Apr 30, 2026Yu Tian, Jiawei Chen, Lifan Zheng +5Skill Evolution Group Relative Policy Optimization
Distributional Alignment Games for Answer-Level Fine-Tuning
Apr 29, 2026Mehryar Mohri, Jon Schneider, Yifan WuLarge Language Model Alignment Finetuning
DGLight: DQN-Guided GRPO Fine-Tuning of Large Language Models for Traffic Signal Control
Apr 28, 2026Chenbo YuIterative Reinforcement Learning Group Relative Policy Optimization
V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think
Apr 25, 2026Bingda Tang, Yuhui Zhang, Xiaohan Wang +3Group Relative Policy Optimization Generative Models
Hidden States Know Where Reasoning Diverges: Credit Assignment via Span-Level Wasserstein Distance
Apr 25, 2026Xinzhu Chen, Wei He, Huichuan Fan +7Credit Assignment Group Relative Policy Optimization
Towards Temporal Compositional Reasoning in Long-Form Sports Videos
Apr 24, 2026Siyu Cao, Lu Zhang, Ruizhe Zeng +1Video Temporal Grounding Dense Temporal Annotation
GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning
Apr 22, 2026Jingyi Wang, Lei Zhu, Tengjin Weng +8Reinforcement Learning With Verifiable Reward Group Relative Policy Optimization
M $^{2}$ GRPO: Mamba-based Multi-Agent Group Relative Policy Optimization for Biomimetic Underwater Robots Pursuit
Apr 21, 2026Yukai Feng, Zhiheng Wu, Zhengxing Wu +2Underwater Robots Multi-Agent Reinforcement Learning
Learning to Credit the Right Steps: Objective-aware Process Optimization for Visual Generation
Apr 21, 2026Rui Li, Ke Hao, Yuanzhi Liang +4Denoising Trajectory Visual Generation
Reinforcement Learning Improves LLM Accuracy and Reasoning in Disease Classification from Radiology Reports
Apr 21, 2026Yishu Wei, Yi Lin, Adam Flanders +2Radiology Report Generation Disease Detection
UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models
Apr 20, 2026Jiaqi Wang, Haoge Deng, Ting Pan +5Group Relative Policy Optimization Generative Models
Negative Advantages Is a Double-Edged Sword: Calibrating advantages in GRPO for Search Agents
Apr 20, 2026Jiayi Wu, Ruobing Xie, Zeqian Huang +6Group Relative Policy Optimization Search Agents
OmniVLA-RL: A Vision-Language-Action Model with Spatial Understanding and Online RL
Apr 20, 2026Haoxiang Jie, Yaoyuan Yan, Xiangyu Wei +4Vision-Language-Action Models Spatial Reasoning
CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search
Apr 19, 2026Hansi Zeng, Liam Collins, Bhuvesh Kumar +2Agentic Search Reranking
MCPO: Mastery-Consolidated Policy Optimization for Large Reasoning Models
Apr 18, 2026Zhaokang Liao, Yingguo Gao, Yi Yang +2Reinforcement Learning With Verifiable Reward Group Relative Policy Optimization
S-GRPO: Unified Post-Training for Large Vision-Language Models
Apr 17, 2026Yuming Yan, Kai Tang, Sihong Chen +4Vision-Language Model Adaptation Large Vision Language Models
Improving Heart-Focused Medical Question Answering in LLMs via Variance-Aware Rubric Rewards with GRPO
Apr 17, 2026Arash Ahmadi, Parisa Masnadi, Sarah Sharif +3Large Language Model Post-Training Rubric-Based Reinforcement Learning
RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework
Apr 16, 2026Hao Gao, Shaoyu Chen, Yifan Zhu +4Diffusion Planning Autonomous Driving
Targeted Exploration via Unified Entropy Control for Reinforcement Learning
Apr 16, 2026Chen Wang, Lai Wei, Yanzhi Zhang +5Reinforcement Learning With Verifiable Reward Group Relative Policy Optimization
Region-Constrained Group Relative Policy Optimization for Flow-Based Image Editing
Apr 10, 2026Zhuohan Ouyang, Zhe Qian, Wenhuo Cui +1Image Editing Group Relative Policy Optimization
Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering
Mar 30, 2026Yanjie Zhang, Yafei Li, Rui Sheng +5Chart Visual Reasoning
Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment
Feb 17, 2026Jialu Wang, Heinrich Peters, Asad A. Butt +6Preference Alignment Group Relative Policy Optimization
GRRM: Group Relative Reward Modeling for Machine Translation
Feb 15, 2026Sen Yang, Shanbo Cheng, Lu Xu +2Machine Translation Quality Machine Translation
F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare
Feb 6, 2026Daniil Plyusov, Alexey Gorbatovski, Boris Shaposhnikov +4Group Relative Policy Optimization Reinforcement Learning With Verifiable Reward
Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO
Feb 6, 2026Yunze Tong, Mushui Liu, Canyu Zhao +7Generative Flow Networks Flow-Grpo
The Optimal Token Baseline: Variance Reduction for Long-Horizon LLM-RL
Feb 6, 2026Yingru Li, Jiawei Xu, Ziniu Li +10Group Relative Policy Optimization Logit Lens
Constrained Group Relative Policy Optimization
Feb 5, 2026Roger Girgis, Rodrigue de Schaetzen, Luke Rowe +3Group Relative Policy Optimization
BRIDGE: Bridging Reasoning In Distillation Gap Elimination via Structure-Aware Masking
Feb 5, 2026Bowen Yu, Sheng Zhang, Binhao Wang +8Chain-Of-Thought Distillation Curriculum
Policy of Thoughts: Scaling Test-Time Training for LLM Reasoning via Online Policy Evolution
Jan 28, 2026Zhengbo Jiao, Hongyu Xian, Qinglong Wang +5Large Language Model Reasoning Group Relative Policy Optimization
KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering
Dec 10, 2025Xin Sun, Zhongqi Chen, Xing Zheng +6Large Language Model Reasoning Knowledge Graphs
Iterative GRPO: Batch-Online Policy Iteration for Multi-Turn RL via Single-Turn RLHF
Nov 26, 2025Daniel R. Jiang, Ankur Samanta, Yukai Yang +3Group Relative Policy Optimization Reinforcement Learning From Human Feedback
Rethinking Reward Signals in Video GRPO: When Scores Become Targets
Nov 24, 2025Rui Li, Yuanzhi Liang, Ziqi Ni +3Group Relative Policy Optimization
Strengthening LLMs for Tabular Prediction with Structural Priors
Oct 20, 2025Pengxiang Cai, Zihao Gao, Wanchen Lian +2Tabular Learning Large Language Model Post-Training
LLP: LLM-Based Product Pricing in E-commerce
Oct 10, 2025Hairu Wang, Sheng You, Qiheng Zhang +5Prices Products
AD-FM: Multimodal LLMs for Anomaly Detection via Multi-Stage Reasoning and Fine-Grained Reward Optimization
Aug 6, 2025Jingyi Liao, Yongyi Su, Rong-Cheng Tu +6Zero-Shot Anomaly Detection Anomaly Detection
MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE
Jul 29, 2025Junzhe Li, Yutao Cui, Tao Huang +8Flow-Grpo Group Relative Policy Optimization
Complementing reinforcement learning with SFT through logit averaging in the post training of LLMs
Date pendingXingwei Gan, Ying ZhuGroup Relative Policy Optimization Reinforcement Learning Post-Training
TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas
Date pendingAi Jian, Xiaoyun Zhang, Eryu Guo +6Text-To-Sql Schema

May 6, 2026 · cs.LGJ/K move · Enter open · S save

Rollout Pass-Rate Control: Steering Binary-Reward RL Toward Its Most Informative Regime

Tianshu Zhu, Wenyu Zhang, Xiaoying Zuo, Lun Tian+7

Baidu

Agentic reinforcement learning (RL) for software engineering spends much of its compute on stateful trajectories whose grouped binary rewards are highly skewed and weakly contrastive. We frame this as pass-rate control and show that the binary reward-side signal is strongest near a 50% rollout pass rate under four criteria: reward entropy, group-filtering survival, leave-one-out (RLOO) advantage energy under Group Relative Policy Optimization (GRPO), and success-failure pair count. We propose Prefix Sampling (PS), which replays self-generated trajectory prefixes to steer skewed groups toward this regime: successful prefixes give mostly failing groups a head start, while failing prefixes handicap mostly passing groups. Replayed states are reconstructed through the existing rollout path, and replayed tokens are masked from the loss so optimization applies only to current-policy continuations. On SWE-bench Verified, PS reaches the baseline high-score regime within evaluation variability while delivering 2.01x and 1.55x end-to-end wall-clock speedups on Qwen3-14B and Qwen3-32B; the 14B peak improves from 0.274 to 0.295. AIME 2025 experiments on 4B and 8B show the same pass-rate-control pattern, and 4B ablations attribute gains to replay, bidirectional coverage, and adaptive control.

Rollout Group Relative Policy Optimization Steering

Open paper Ask about it PDF