Group Relative Policy Optimization

Also known as GRPO

Follow this topic Ask about this topic

Latest papers 305

48 papers in the last four weeks, up 109% on the four weeks before. 0.3% of all new papers.

All topics

Can the Environment Speak for Itself? $T^{2}$ -GRPO: A Turn-Trajectory Group Relative Policy Optimization for Caregiver Agents
Jun 7, 2026Yutong Song, Jiang Wu, Pengfei Zhang +4Reward Shaping Healthcare
University of California, Irvine · Independent Researcher · Kennesaw State University
sGPO: Trading Inference FLOPs for Training Efficiency in RLVR
Jun 7, 2026Shivchander Sudalairaj, Kai Xu, Akash Srivastava +1Group Relative Policy Optimization Adaptive Sampling
AI Innovation, Red Hat · Core AI, IBM
Momentum for Reasoning: Dense Intrinsic Signals in Policy Optimization
Jun 7, 2026Hao Chen, Zhanming Shen, Liyao Li +8Intrinsic Reward Methods Reinforcement Learning
Zhejiang University · The Chinese University of Hong Kong · Eastern Institute of Technology
Adaptive Loss Balancing for Noise-Robust GRPO in Generative Recommendation
Jun 7, 2026Kewei Xu, Junbo Qi, Yanyan Zou +3Group Relative Policy Optimization Recommender Systems
Waseda University Tokyo, Japan · University of Electronic Science and Technology of China Chengdu, China
GRPO Does Not Close the Multi-Agent Coordination Gap
Jun 5, 2026Najmul Hasan, Prashanth BusiReddyGariMulti-Agent System Optimization Multi-Agent Coordination
Department of Mathematics and Computer Science, University of North Carolina at Pembroke, Pembroke, NC, USA
AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO
Jun 5, 2026Jiazi Bu, Pengyang Ling, Yujie Zhou +8T2I Generation Group Relative Policy Optimization
1Shanghai Jiao Tong University · 2S-Lab, Nanyang Technological University · 3Shanghai AI Laboratory +7
MDP-GRPO: Stabilized Group Relative Policy Optimization for Multi-Constraint Instruction Following
Jun 4, 2026Mohammad Mahdi Salmani-Zarchi, Zahra Rahimi, Heshaam Faili +1Group Relative Policy Optimization Instruction Following
Department of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran · Department of Statistics, Mathematics and Computer Science, Allameh Tabataba’i University, Tehran, Iran
SALT: When More Rollouts Don't Help in Group-Based Policy Optimization and How to Make Them Matter
Jun 4, 2026Powei Chang, Jinpeng Zhang, Chaoqun Sun +6Policy Gradient Group Relative Policy Optimization
Bilibili Inc. · Fudan University · Zhejiang University
TAPO: Tool-Aware Policy Optimization via Credit Transfer for Multimodal Search Agents
Jun 4, 2026Chengqi Dong, Chuhuai Yue, Hang He +6Multimodal IR Token-Level Credit Assignment
University of Science and Technology of China · 2Meituan
AsyncWebRL: Efficient Multi-Step RL for Visual Web Agents
Jun 4, 2026Hao Bai, Rui Yang, Chenlu Ye +3Asynchronous RL Reinforcement Learning
1UIUC · 2Microsoft · 3CMU
Selective-Advantage Entropy-Adaptive Horizon GRPO: Asymmetric Token-Level Discounting for Efficient Reinforcement Learning of Language Models
Jun 3, 2026Chirag Chawla, Rohan Charudatt Salvi, Madhav S. BaidyaReinforcement Learning RL for Language Model Reasoning
Indian Institute of Technology (BHU), Varanasi, India · Department of Computer Science, University of Illinois Chicago, IL 60607, USA
BiasGRPO: Stabilizing Bias Mitigation in High-Variance Reward Landscapes via Group-Relative Policy Optimization
Jun 3, 2026Saket Reddy, Ke Yang, ChengXiang ZhaiReward Modeling RL for Language Models
University of Illinois - Urbana-Champaign
Rollout-Level Advantage-Prioritized Experience Replay for GRPO
Jun 3, 2026Gyeongtae Yoo, Sanghyeok Park, Soohyuk Jang +2RL for Language Model Reasoning Group Relative Policy Optimization
Department of Electrical and Computer Engineering, Seoul National University · Interdisciplinary Program in AI, Seoul National University · AIIS, ASRI, INMC, and ISRC, Seoul National University
SD-GRPO: Verifiable Segment Decomposition for Long-Form Vision-Language Generation
Jun 2, 2026Hyunwoong Kim, Seongeun Lee, Hannah Yun +2Vision-Language Models Group Relative Policy Optimization
DEEPNOID Inc., Seoul, South Korea
FGRPO: Federated GRPO with Adaptive Aggregation on Non-IID Data
Jun 2, 2026Pengyu Chen, Shaowei Li, Kai Wang +4Federated Learning Aggregation Federated RL
School of Computer Science and Technology, Shandong University, Qingdao China · School of Mathematical Science, Peking University, China · School of Computer Science and Artificial Intelligence, Shanghai University of Finance and Economics, Shanghai, China +1
ASymPO: Asymmetric-Scale Policy Optimization for Asynchronous LLM Post-Training Without Behavior Information
Jun 2, 2026Zehua Liu, Yuxuan Yao, Xiaojin Fu +2Asynchronous RL Reinforcement Learning
Huawei Technologies
Towards Precise Intent-Aligned VLA Aerial Navigation via Expert-Guided GRPO
Jun 1, 2026Tianyang Chen, Wenjun Li, Xin zhou +2UAV Navigation Group Relative Policy Optimization
1Zhejiang University · 2Differential Robotics
Faster Synchronous On-Policy RL via Straggler-Aware Group Sizing
Jun 1, 2026Azal Ahmad Khan, Ammar Ahmed, Zeshan Fayyaz +3Reinforcement Learning Group Relative Policy Optimization
University of Minnesota · University of Waterloo · Argonne National Laboratory
Pave-GRPO: Beyond Instantaneous Guidance through Principled Average Velocity Decomposition
Jun 1, 2026Pengyang Ling, Jiazi Bu, Yujie Zhou +6Diffusion Model Alignment Group Relative Policy Optimization
University of Science and Technology of China, China · Shanghai Jiao Tong University, China · Fudan University, China +3
CAST: Non-Privileged Clipped Asymmetric Self-Teaching with Advantage Flipping for GRPO
May 29, 2026Yang Li, Gongle Xue, Yijia Guo +3RL for Language Model Reasoning Group Relative Policy Optimization
School of Software and Microelectronics, Peking University, Beijing · School of Artificial Intelligence, Peking University, Beijing · School of Computer Science, Peking University, Beijing +1
Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO
May 29, 2026Yiming Ren, Yiran Xu, Zicheng Lin +8Reinforcement Learning RL for Language Model Reasoning
Tsinghua University · Shanghai AI Laboratory · The Chinese University of Hong Kong +1
VeriGate: Verifier-Gated Step-Level Supervision for GRPO
May 28, 2026Aakriti Agrawal, Minghui Liu, Furong HuangProcess Reward Models RL for Language Model Reasoning
University of Maryland, College Park
HPO: Hysteretic Policy Optimization for Stable and Efficient Training under Sparse-Reward Regime
May 28, 2026Mohamed Sana, Nicola Piovesan, Antonio De Domenico +2Group Relative Policy Optimization Policy Optimization
Paris Research Center, Huawei Technologies, Boulogne-Billancourt, France · Huawei Technologies, China
Deconstructing Spatial Complexity: Hierarchical Decomposition for LLM Spatial Reasoning
May 27, 2026Yi Wang, Haojie Lu, Zhaofan Zhang +2Hierarchical Planning RL for Language Model Reasoning
The Hong Kong University of Science and Technology (Guangzhou)
BPPO: Binary Prefix Policy Optimization for Efficient GRPO-Style Reasoning RL with Concise Responses
May 27, 2026Qingfei Zhao, Huan Song, Shuyu Tian +2RL for Language Model Reasoning Group Relative Policy Optimization
1TeleAI · 2Shanghai Jiao Tong University
Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning
May 26, 2026Xin Cheng, Shuo He, Lang Feng +4Group Relative Policy Optimization Credit Assignment in RL
Nanyang Technological University, Singapore · Tongyi Lab, Alibaba Group · Southeast University, China
Spend Your Rollouts Where It Counts: Rollout Allocation for Group-Based RL Post-Training
May 26, 2026Woojeong Kim, Ziyi Yang, Jing Nathan Yan +1Reinforcement Learning RL for Language Model Reasoning
Databricks · Cornell University
DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning
May 25, 2026Guochao Jiang, Jingyi Song, Guofeng Quan +3Multi-Objective Reinforcement Learning RL for Language Model Reasoning
Alibaba Cloud Computing
DeepSeekMath Meets Order Book: Group-Aware Policy Optimization for High-Frequency Directional Trading
May 25, 2026Sayak Charabarty, Souradip PalGroup Relative Policy Optimization Proximal Policy Optimization
Department of Computer Science Northwestern University Evanston, IL 60208, USA · School of Electrical and Computer Engineering Purdue University West Lafayette, IN 47906, USA
CRPO: Character-centric Group Relative Policy Optimization for Role-aware Reasoning in Role-playing Agents
May 25, 2026Yihong Tang, Kehai Chen, Liang Yue +2RL for Language Models Persona Consistency
Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China · Shenzhen Loop Area Institute (SLAI), Shenzhen, China · The Chinese University of Hong Kong, Shenzhen, China

Jun 7, 2026J/K move · Enter open · S save

Can the Environment Speak for Itself? $T^{2}$ -GRPO: A Turn-Trajectory Group Relative Policy Optimization for Caregiver Agents

Yutong Song, Jiang Wu, Pengfei Zhang, Wenjun Huang+3

University of California, Irvine · Independent Researcher · Kennesaw State University

Reward Shaping Healthcare Group Relative Policy Optimization Constrained RL Long-Horizon LLM Agents

Open paper AskPDF arXiv

Optimizing large language models (LLMs) for long-horizon caregiver agents requires balancing delayed task objectives with immediate environment dynamics, such as patient distress and resistance. In dementia care, this balance is especially difficult: trajectory level rewards are too sparse for turn level credit assignment, while external LLM-based evaluators are costly and can misread fragmented or indirect patient responses. To address this issue, we propose Turn-Trajectory Group Relative Policy Optimization (\textbf{T

^{2}

-GRPO}), a framework that decouples caregiver RL into two normalized reward horizons and enforces safety through a binary hard veto.

T^2

-GRPO derives dense turn-level rewards directly from environment state transitions, measuring changes in patient distress and resistance from a frozen dementia patient simulator. These environment-grounded rewards are combined with trajectory-level evaluations through independent centered-rank normalization, which preserves heterogeneous reward signals and mitigates reward collapse. Extensive experiments on dementia caregivers show that T

^{2}

-GRPO outperforms competitive baselines, indicating a substantial improvement for emotionally sensitive caregiver scenarios that effectively handles immediate patient feedback, long-term care outcomes, and safety constraints.