Better Call Group Relative Policy Optimization

Follow this topic Ask about this topic

Momentum

1 paper in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 24

All topics

Certified Selective Automation of LLM Agent Evaluation
Sep 28, 2026Chengguang Gan, Yunhao Liang, Qinghao Zhang +1Agentic Evaluations Automated
Independent Researcher · University of Chinese Academy of Sciences · Pusan National University +1
Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation
Sep 2, 2026Zhiwei Zhang, Zechen Sun, Fei Zhao +6Efficient On-Policy Distillation Teacher
AllSpark Team
GRASP: Reinforcing Language Model Anonymizers with Group Relative Policy Optimization
Aug 6, 2026Sajjad Ghiasvand, Nader SehatbakhshAnonymization Better Call Group Relative Policy Optimization
Electrical and Computer Engineering Department, UC Santa Barbara1 · Electrical and Computer Engineering Department, UC Los Angeles2
Teaching MLLMs to Say No: Generalized Referring Expression Comprehension via Refusal Calibrated GRPO
Aug 5, 2026Xuzheng Yang, Jun Ling, Tao Huang +2Refusals LLM Reasoning Strategies
School of Computer Science and Engineering, University of Electronic Science and Technology of China
Not All Tokens Deserve Equal Credit: Counterfactual Sensitivity Credit Reallocation for Long-CoT Reasoning
Jul 30, 2026Qiangqiang He, Zhongheng Wu, ZiJian WangCredit Assignment Reinforcement Learning With Verifiable Reward
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China · Institute of Wireless Communications Technology, Shanghai Jiao Tong University, Shanghai, China
When Synthetic Speech Is All You Have: Better Call GRPO
Jul 9, 2026Shashi Kumar, Yanis Labrak, Hasindri Watawana +5Flow-Grpo Speech-To-Text Alignment
Idiap Research Institute, Martigny, Switzerland · EPFL, Lausanne, Switzerland · Uniphore, U.S.A. +1
Scaling Laws for Collapse in Asynchronous GRPO
Jul 1, 2026Jingwei Song, Haofeng Xu, Jie Xiao +7Parallel Rollouts Better Call Group Relative Policy Optimization
The University of Hong Kong · Shanghai Jiao Tong University · Gradient +2
Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models
Jun 30, 2026Lang Cao, Renhong Chen, Luyi Li +3Flow-Matching Vision-Language-Action Offline Reinforcement Learning
Zioneer Robot Team
ThinkDeception: A Progressive Reinforcement Learning Framework for Interpretable Multimodal Deception Detection
Jun 17, 2026Jinhao Song, Shan Liang, Yiqun Yue +2Deception Multimodal Reasoning
Xi’an Jiaotong-Liverpool University · Suzhou, China
Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning
Jun 17, 2026Xiaoyue Xu, Sikui Zhang, Xiaorong Wang +2Large Language Model Reinforcement Learning Long-Context Reasoning
OpenBMB · Tsinghua University
Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents
Jun 10, 2026Tianyu Ding, Jianhong Xin, Juan Pablo De la Cruz WeinsteinBetter Call Group Relative Policy Optimization Policy Gradient
Amazon Web Services
FGRPO: Federated GRPO with Adaptive Aggregation on Non-IID Data
Jun 2, 2026Pengyu Chen, Shaowei Li, Kai Wang +4Better Call Group Relative Policy Optimization Flow-Grpo
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
RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning
May 31, 2026Yixiu Mao, Yun Qu, Qi Wang +2Reinforcement Learning With Verifiable Reward Better Call Group Relative Policy Optimization
Department of Automation, Tsinghua University
CAST: Non-Privileged Clipped Asymmetric Self-Teaching with Advantage Flipping for GRPO
May 29, 2026Yang Li, Gongle Xue, Yijia Guo +3Reinforcement Learning With Verifiable Reward Better Call 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
Touch-R1: Reinforcing Touch Reasoning in MLLMs
May 26, 2026Yingxin Lai, Yafei Zhou, Fucai Zhu +2Tactile Multimodal Large Language Models
1Xiamen University · 5Daimon Robotics · 2Great Bay University +2
CRPO: Character-centric Group Relative Policy Optimization for Role-aware Reasoning in Role-playing Agents
May 25, 2026Yihong Tang, Kehai Chen, Liang Yue +2Better Call Group Relative Policy Optimization Role-Playing Agents
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
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
Meta AI · The Chinese University of Hong Kong
KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration
May 14, 2026Ruicheng Zhang, Kaixi Cong, Jun Zhou +5Autoregressive Video Generation Repair-Based Group-Relative Policy Optimization
Tsinghua University · Video Rebirth · HKUST
Breaking $\textit{Winner-Takes-All}$ : Cooperative Policy Optimization Improves Diverse LLM Reasoning
May 12, 2026Haoxuan Chen, Tianming Liang, Wei-Shi Zheng +1Better Call Group Relative Policy Optimization LLM Reasoning Strategies
1ISEE Lab, Sun Yat-sen University
Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models
May 8, 2026Xiaoze Liu, Dhananjay Ram, Yuting Zhang +3Reinforcement Learning Post-Training Better Call Group Relative Policy Optimization
1Purdue University · *Work done during an internship at Amazon. · 2AWS Agentic AI
Cost-Aware Learning
Apr 30, 2026Clara Mohri, Amir Globerson, Haim Kaplan +2Better Call Group Relative Policy Optimization Stochastic Gradient Descent
Kempner Institute · Harvard University · Google Research +1
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 Better Call Group Relative Policy Optimization
Tsinghua University · Huawei Noah’s Ark Lab · Shenzhen University
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
School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China, and also with the Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China · State Key Laboratory for Turbulence and Complex Systems, Department of Advanced Manufacturing and Robotics, College of Engineering, Peking University, Beijing 100871, China
Improving Heart-Focused Medical Question Answering in LLMs via Variance-Aware Rubric Rewards with GRPO
Apr 17, 2026Arash Ahmadi, Parisa Masnadi, Sarah Sharif +3Better Call Group Relative Policy Optimization
School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK, USA · Intelligent Neuromorphic and Quantum Understanding for Innovative Research and Engineering (INQUIRE) Laboratory, University of Oklahoma, Norman, OK, USA · Data Science and Analytics Institute, University of Oklahoma, Norman, OK, USA +3

Sep 28, 2026, cs.CLJ/K move · Enter open · S save

Certified Selective Automation of LLM Agent Evaluation

Chengguang Gan, Yunhao Liang, Qinghao Zhang, Shiwen Ni

Independent Researcher · University of Chinese Academy of Sciences · Pusan National University+1

Agentic Evaluations Automated Certificates Text Corpora Better Call Group Relative Policy Optimization

Open paper AskPDF arXiv

Evaluating LLM agents still ends with a human reading trajectories, because automatic judges carry no guarantee on how often they are wrong. We ask the operational question: what fraction of agent evaluation can a judge take over, with a certificate that the error rate among auto-decided trajectories stays below a budget alpha? Agent corpora resist the standard answer: many agents attempt the same tasks, so trajectories arrive in correlated clusters, and the i.i.d. certificates of existing selective-judging methods can overstate what is safe: a naive certificate can claim 98% automation while its realized error exceeds the budget in 17.5% of task resamples. We introduce a task-level bootstrap certificate that is valid in every regime we test while matching the naive certificate's coverage; finite-sample cluster-valid alternatives certify nothing at realistic task counts. Under this certificate, a 4B logprob judge trained with SFT and reject-weighted GRPO certifies 0.30-0.59 of evaluation on tool-use and web corpora at alpha=0.1, the only judge, among strongly elicited frontier models, certifying on both headline corpora. Certified coverage is predictable before training from base rate and discrimination alone (leave-one-corpus-out R^2=0.96). Finally, the certificate doubles as a self-training filter: pseudo-labels harvested inside certified regions have contamination bounded by alpha by construction (realized 0.000-0.041 across six harvests), letting a judge enter an unseen domain at in-domain strength with zero target training labels.

Momentum

Related topics

Latest papers 24