English
Related papers

Related papers: Beyond Uniform Credit Assignment: Selective Eligib…

200 papers

We propose FSPO (Fair Sequence Policy Optimization), a sequence-level reinforcement learning method for LLMs that enforces length-fair clipping on the importance-sampling (IS) weight. We study RL methods with sequence-level IS and identify…

Machine Learning · Computer Science 2025-10-14 Hanyi Mao , Quanjia Xiao , Lei Pang , Haixiao Liu

Achieving fast and stable off-policy learning in deep reinforcement learning (RL) is challenging. Most existing methods rely on semi-gradient temporal-difference (TD) methods for their simplicity and efficiency, but are consequently…

Machine Learning · Computer Science 2025-09-22 Esraa Elelimy , Brett Daley , Andrew Patterson , Marlos C. Machado , Adam White , Martha White

Large language models (LLMs) are increasingly applied to complex reasoning tasks that require executing several complex steps before receiving any reward. Properly assigning credit to these steps is essential for enhancing model…

Training Large Language Models (LLMs) for reasoning tasks is increasingly driven by Reinforcement Learning with Verifiable Rewards (RLVR), where Proximal Policy Optimization (PPO) provides a principled framework for stable policy updates.…

Machine Learning · Computer Science 2026-01-13 Xue Gong , Qi Yi , Ziyuan Nan , Guanhua Huang , Kejiao Li , Yuhao Jiang , Ruibin Xiong , Zenan Xu , Jiaming Guo , Shaohui Peng , Bo Zhou

Reinforcement learning is crucial for aligning large language models to perform complex reasoning tasks. However, current algorithms such as Group Relative Policy Optimization suffer from coarse grained, sequence level credit assignment,…

Machine Learning · Computer Science 2026-05-11 Hongbo Jin , Rongpeng Zhu , Zhongjing Du , Xu Jiang , Jingqi Tian , Qiaoman Zhang , Jiayu Ding

Despite their sophisticated general-purpose capabilities, Large Language Models (LLMs) often fail to align with diverse individual preferences because standard post-training methods, like Reinforcement Learning with Human Feedback (RLHF),…

Reinforcement learning from verifiable rewards (RLVR) is an emerging paradigm for improving the reasoning ability of large language models. However, standard on-policy training discards rollout experiences after a single update, leading to…

Machine Learning · Computer Science 2026-03-03 Runzhe Zhan , Yafu Li , Zhi Wang , Xiaoye Qu , Dongrui Liu , Jing Shao , Derek F. Wong , Yu Cheng

Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of large language models (LLMs) on mathematics and programming tasks, but standard approaches that optimize single-attempt accuracy can inadvertently…

Machine Learning · Computer Science 2026-02-27 Devan Shah , Owen Yang , Daniel Yang , Chongyi Zheng , Benjamin Eysenbach

Reinforcement learning with verifiable rewards (RLVR) has enabled large language models (LLMs) to achieve remarkable breakthroughs in reasoning tasks with objective ground-truth answers, such as mathematics and code generation. However, a…

Computation and Language · Computer Science 2025-06-12 Ruipeng Jia , Yunyi Yang , Yongbo Gai , Kai Luo , Shihao Huang , Jianhe Lin , Xiaoxi Jiang , Guanjun Jiang

Reinforcement learning from verifiable rewards has significantly advanced the reasoning capabilities of large language models. However, Group Relative Policy Optimization (GRPO) typically assigns a uniform, sequence-level advantage to all…

Machine Learning · Computer Science 2026-04-06 Song Yu , Li Li , Wenwen Zhao , Zhisheng Yang

Training Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR) - where models iteratively reason, generate code, and verify through execution - remains challenging for existing reinforcement learning (RL) approaches.…

Machine Learning · Computer Science 2026-04-21 Yifeng Ding , Hung Le , Songyang Han , Kangrui Ruan , Zhenghui Jin , Varun Kumar , Zijian Wang , Anoop Deoras

Recently, online Reinforcement Learning with Verifiable Rewards (RLVR) has become a key paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing methods typically treat all training samples…

Artificial Intelligence · Computer Science 2025-09-30 Shijie Zhang , Guohao Sun , Kevin Zhang , Xiang Guo , Rujun Guo

RLVR has enhanced the reasoning capabilities of Large Language Models (LLMs) across various tasks. However, GRPO, a representative RLVR algorithm, suffers from a critical limitation: when all responses within a group are either entirely…

Machine Learning · Computer Science 2025-09-24 Gongrui Nan , Siye Chen , Jing Huang , Mengyu Lu , Dexun Wang , Chunmei Xie , Weiqi Xiong , Xianzhou Zeng , Qixuan Zhou , Yadong Li , Xingzhong Xu

Reinforcement learning with verifiable rewards has shown notable effectiveness in enhancing large language models (LLMs) reasoning performance, especially in mathematics tasks. However, such improvements often come with reduced outcome…

Artificial Intelligence · Computer Science 2026-02-03 Chenyi Li , Yuan Zhang , Bo Wang , Guoqing Ma , Wei Tang , Haoyang Huang , Nan Duan

Reinforcement learning with verifiable rewards (RLVR) has become a standard recipe for improving large language models (LLMs) on reasoning tasks, with Group Relative Policy Optimization (GRPO) widely used in practice. Yet GRPO wastes…

Machine Learning · Computer Science 2025-10-13 Yunzhen Feng , Parag Jain , Anthony Hartshorn , Yaqi Duan , Julia Kempe

Reinforcement learning with verifiable rewards (RLVR) is effective for training large language models on deterministic outcome reasoning tasks. Prior work shows RLVR works with few prompts, but prompt selection is often based only on…

Machine Learning · Computer Science 2026-05-07 Yujuan Pang , Jiaxin Li , Xin Sheng , Ran Peng , Yong Ma

Reinforcement Learning with Verifiable Rewards (RLVR) is increasingly viewed as a tree pruning mechanism. However, we identify a systemic pathology termed Recursive Space Contraction (RSC), an irreversible collapse driven by the combined…

Artificial Intelligence · Computer Science 2026-02-06 Tianyi Wang , Long Li , Hongcan Guo , Yibiao Chen , Yixia Li , Yong Wang , Yun Chen , Guanhua Chen

Group-Relative Policy Optimization (GRPO) has emerged as the standard for training reasoning capabilities in large language models through reinforcement learning. By estimating advantages using group-mean rewards rather than a learned…

Artificial Intelligence · Computer Science 2026-03-06 Anisha Garg , Claire Zhang , Nishit Neema , David Bick , Ganesh Venkatesh , Joel Hestness

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

Group relative policy optimization (GRPO) has demonstrated significant potential in improving the reasoning capabilities of large language models (LLMs) via reinforcement learning. However, its practical deployment is impeded by an…

Machine Learning · Computer Science 2025-09-29 Yizhou Zhang , Ning Lv , Teng Wang , Jisheng Dang