English
Related papers

Related papers: Your Group-Relative Advantage Is Biased

200 papers

Current reinforcement learning(RL) methods are broadly applicable and powerful in verifiable settings where scalar rewards can be provided. However, in open-ended generation tasks, verifying the correctness of responses remains challenging,…

Artificial Intelligence · Computer Science 2026-05-19 Guining Cao , Jiaxin Peng , Chu Zeng , Yu Zhao , Shuangyong Song , Yongxiang

Inspired by the success of reinforcement learning (RL) in refining large language models (LLMs), we propose AR-GRPO, an approach to integrate online RL training into autoregressive (AR) image generation models. We adapt the Group Relative…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Shihao Yuan , Yahui Liu , Yang Yue , Jingyuan Zhang , Wangmeng Zuo , Qi Wang , Fuzheng Zhang , Guorui Zhou

Large Language Models (LLMs) empowered with Tool-Integrated Reasoning (TIR) can iteratively plan, call external tools, and integrate returned information to solve complex, long-horizon reasoning tasks. Agentic Reinforcement Learning…

Computation and Language · Computer Science 2026-01-21 Jianghao Su , Xia Zeng , Luhui Liu , Chao Luo , Ye Chen , Zhuoran Zhuang

Group Relative Policy Optimization (GRPO) performs coarse-grained credit assignment in reinforcement learning with verifiable rewards (RLVR) by assigning the same advantage to all tokens in a rollout. Process reward models can provide…

Computation and Language · Computer Science 2026-04-28 Xinzhu Chen , Wei He , Huichuan Fan , Wenzhe Niu , Zhongxiang Sun , Xuanru Wang , Jiuchong Gao , Jinghua Hao , Renqing He , Weijie Yu

In this work, we investigate how explicitly modeling problem's difficulty prior information shapes the effectiveness of reinforcement learning based fine-tuning for multimodal reasoning. Our exploration mainly comprises of following three…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Mingrui Chen , Haogeng Liu , Hao Liang , Huaibo Huang , Wentao Zhang , Ran He

Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising paradigm for post-training large language models (LLMs) on complex reasoning tasks. Yet, the conditions under which RLVR yields robust generalization remain…

Machine Learning · Computer Science 2026-03-05 Brian Lu , Hongyu Zhao , Shuo Sun , Hao Peng , Rui Ding , Hongyuan Mei

Fine-tuning pre-trained generative models with Reinforcement Learning (RL) has emerged as an effective approach for aligning outputs more closely with nuanced human preferences. In this paper, we investigate the application of Group…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Matteo Gallici , Haitz Sáez de Ocáriz Borde

Reinforcement Learning with Verifiable Rewards (RLVR) can elicit strong multi-step reasoning, yet it often encourages overly verbose traces. Moreover, naive length penalties in group-relative optimization can severely hurt accuracy. We…

Computation and Language · Computer Science 2026-02-03 Keqin Peng , Yuanxin Ouyang , Xuebo Liu , Zhiliang Tian , Ruijian Han , Yancheng Yuan , Liang Ding

Group Relative Policy Optimization (GRPO) has been a key driver of recent progress in reinforcement learning with verifiable rewards (RLVR) for large language models, but it is typically trained in a low-staleness, near-on-policy regime…

Machine Learning · Computer Science 2026-05-19 Minghao Tian , Yunfei Xie , Chen Wei

Group Relative Policy Optimization (GRPO) has been shown to be an effective algorithm when an accurate reward model is available. However, such a highly reliable reward model is not available in many real-world tasks. In this paper, we…

Machine Learning · Computer Science 2026-01-12 Yuki Ichihara , Yuu Jinnai , Tetsuro Morimura , Mitsuki Sakamoto , Ryota Mitsuhashi , Eiji Uchibe

Ensuring reliability in modern software systems requires rigorous pre-production testing across highly heterogeneous and evolving environments. Because exhaustive evaluation is infeasible, practitioners must decide how to allocate limited…

Software Engineering · Computer Science 2025-10-08 Yu Zhu

Reinforcement learning (RL) has significantly improved the reasoning ability of large language models. However, current reward models underperform in challenging reasoning scenarios and predominant RL training paradigms rely on rule-based…

Computation and Language · Computer Science 2025-07-30 Meng Zhou , Bei Li , Jiahao Liu , Xiaowen Shi , Yang Bai , Rongxiang Weng , Jingang Wang , Xunliang Cai

Reinforcement learning from human feedback (RLHF) aligns large language models (LLMs) by encouraging their generations to have high rewards, using a reward model trained on human preferences. To prevent the forgetting of pre-trained…

Reinforcement Learning with Verifiable Rewards (RLVR) has become a key approach for improving the reasoning abilities of large language models. However, widely used critic-free algorithms such as Group Relative Policy Optimization (GRPO)…

Machine Learning · Computer Science 2026-05-08 Chaoli Mou , Zhan Zhuang , Xinning Chen , Yu Zhang

Reinforcement Learning from Human Feedback (RLHF) is a powerful paradigm for aligning foundation models to human values and preferences. However, current RLHF techniques cannot account for the naturally occurring differences in individual…

Machine Learning · Computer Science 2024-08-20 Sriyash Poddar , Yanming Wan , Hamish Ivison , Abhishek Gupta , Natasha Jaques

The alignment of large language models (LLMs) is crucial for generating helpful and harmless content. Existing approaches leverage preference-based human feedback data to learn the reward function and align the LLM with the feedback data.…

Machine Learning · Computer Science 2024-11-15 Yuang Cai , Yuyu Yuan , Jinsheng Shi , Qinhong Lin

Reinforcement Learning with Verifiable reward (RLVR) on preference data has become the mainstream approach for training Generative Reward Models (GRMs). Typically in pairwise rewarding tasks, GRMs generate reasoning chains ending with…

Computation and Language · Computer Science 2026-05-04 Zongqi Wang , Rui Wang , Yuchuan Wu , Yiyao Yu , Pinyi Zhang , Shaoning Sun , Yujiu Yang , Yongbin Li

Reinforcement Learning with Verifiable Rewards (RLVR) has become a core training stage in recent large language models (LLMs). Its reliance on non-public, high-value prompt sets raises concerns about unauthorized data use, creating a need…

Cryptography and Security · Computer Science 2026-05-12 Yule Liu , Heyi Zhang , Jinyi Zheng , Zhen Sun , Zifan Peng , Jiaheng Wei , Tianshuo Cong , Yilong Yang , Xinlei He

Reinforcement Learning from Verifiable Rewards (RLVR) has recently shown that large language models (LLMs) can develop their own reasoning without direct supervision. However, applications in the medical domain, specifically for question…

Machine Learning · Computer Science 2025-09-22 Mirza Farhan Bin Tarek , Rahmatollah Beheshti

Multimodal reasoning over long-horizon video is challenging due to the need for precise spatiotemporal fusion and alignment across modalities. While recent methods such as Group Relative Policy Optimization (GRPO) have shown promise in this…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Yogesh Kulkarni , Pooyan Fazli