English
Related papers

Related papers: Unveiling Implicit Advantage Symmetry: Why GRPO St…

200 papers

Reinforcement Learning with Verifiable Rewards (RLVR) improves LLM reasoning, yet growing evidence indicates an exploration ceiling: it often reweights existing solution traces rather than discovering new strategies, limiting gains under…

Machine Learning · Computer Science 2026-03-03 Bizhe Bai , Xinyue Wang , Peng Ye , Tao Chen

In real-world applications of reinforcement learning (RL), noise from inherent stochasticity of environments is inevitable. However, current policy evaluation algorithms, which plays a key role in many RL algorithms, are either prone to…

Machine Learning · Computer Science 2019-06-19 Tadashi Kozuno , Dongqi Han , Kenji Doya

Reinforcement Learning with Verifiable Rewards (RLVR) strengthens LLM reasoning, but training often oscillates between {entropy collapse} and {entropy explosion}. We trace both hazards to the mean baseline used in value-free RL (e.g., GRPO…

Machine Learning · Computer Science 2026-03-03 Junkang Wu , Kexin Huang , Jiancan Wu , An Zhang , Xiang Wang , Xiangnan He

Recent advances in large language models (LLMs) have shown that reasoning ability can be significantly enhanced through Reinforcement Learning with Verifiable Rewards (RLVR). Group Relative Policy Optimization (GRPO) has emerged as the de…

Computation and Language · Computer Science 2025-10-13 Jingyu Zhou , Lu Ma , Hao Liang , Chengyu Shen , Bin Cui , Wentao Zhang

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

In this paper, we investigate preference-based reinforcement learning (PbRL), which enables reinforcement learning (RL) agents to learn from human feedback. This is particularly valuable when defining a fine-grain reward function is not…

Machine Learning · Computer Science 2025-11-11 Guojian Wang , Jianxiang Liu , Xinyuan Li , Faguo Wu , Xiao Zhang , Tianyuan Chen , Xuyang Chen

Group Relative Policy Optimization (GRPO) was introduced and used recently for promoting reasoning in LLMs under verifiable (binary) rewards. We show that the mean + variance calibration of these rewards induces a weighted contrastive loss…

Machine Learning · Computer Science 2025-10-22 Youssef Mroueh

Recent work shows that preference alignment objectives can be interpreted as divergence estimators between aligned (preferred) & unaligned (less-preferred) distributions, yielding a principled recipe for designing alignment losses. However,…

Machine Learning · Computer Science 2026-05-12 Rajdeep Haldar , Lantao Mei , Guang Lin , Yue Xing , Qifan Song

Group Relative Policy Optimization (GRPO), which is widely adopted by R1-like reasoning models, has advanced mathematical reasoning. Nevertheless, GRPO faces challenges in reward sparsity, verbosity, and inadequate focus on problem…

Computation and Language · Computer Science 2025-09-23 Jixiao Zhang , Chunsheng Zuo

Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons. While recent LLM-based agents show promise, current prompt-based agents for MLE suffer from behavioral stagnation…

Machine Learning · Computer Science 2026-05-08 Yuzhu Cai , Zexi Liu , Xinyu Zhu , Cheng Wang , Yanfeng Wang , Siheng Chen

Reinforcement learning (RL) plays a central role in large language model (LLM) post-training. Among existing approaches, Group Relative Policy Optimization (GRPO) is widely used, especially for RL with verifiable rewards (RLVR) fine-tuning.…

Reinforcement learning with verifiable rewards (RLVR) has become a practical route to improve large language model reasoning, and Group Relative Policy Optimization (GRPO) is a widely used optimizer in this setting. However, RLVR training…

Machine Learning · Computer Science 2026-05-14 Tue Le , Linh Ngo Van , Trung Le

Alignment methodologies have emerged as a critical pathway for enhancing language model alignment capabilities. While SFT (supervised fine-tuning) accelerates convergence through direct token-level loss intervention, its efficacy is…

Post-training LLMs with Reinforcement Learning, specifically Group Relative Policy Optimization (GRPO), has emerged as a paradigm for enhancing mathematical reasoning. However, standard GRPO relies on scalar correctness rewards that are…

Computation and Language · Computer Science 2026-03-03 Xiwen Chen , Wenhui Zhu , Peijie Qiu , Xuanzhao Dong , Hao Wang , Haiyu Wu , Huayu Li , Aristeidis Sotiras , Yalin Wang , Abolfazl Razi

Group Relative Policy Optimization (GRPO) assigns a single scalar advantage to all tokens in a completion. For structured generations with explicit segments and objectives, this couples unrelated reward signals across segments, leading to…

Machine Learning · Computer Science 2026-02-12 Kirill Pavlenko , Alexander Golubev , Simon Karasik , Boris Yangel

Recent reinforcement learning has enhanced the flow matching models on human preference alignment. While stochastic sampling enables the exploration of denoising directions, existing methods which optimize over multiple denoising steps…

Machine Learning · Computer Science 2026-01-05 Shengjun Zhang , Zhang Zhang , Chensheng Dai , Yueqi Duan

In inverse reinforcement learning (IRL), a learning agent infers a reward function encoding the underlying task using demonstrations from experts. However, many existing IRL techniques make the often unrealistic assumption that the agent…

Machine Learning · Computer Science 2023-01-04 Franck Djeumou , Christian Ellis , Murat Cubuktepe , Craig Lennon , Ufuk Topcu

Recent advancements have established Reinforcement Learning (RL) as a pivotal paradigm for aligning generative models with human intent. However, group-based optimization frameworks (e.g., GRPO) face a critical limitation: the rapid decay…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Sujie Hu , Chubin Chen , Jiashu Zhu , Jiahong Wu , Xiangxiang Chu , Xiu Li

LLM-based search agents are increasingly trained on entity-centric synthetic data to solve complex, knowledge-intensive tasks. However, prevailing training methods like Group Relative Policy Optimization (GRPO) discard this rich entity…

Computation and Language · Computer Science 2026-02-25 Yida Zhao , Kuan Li , Xixi Wu , Liwen Zhang , Dingchu Zhang , Baixuan Li , Maojia Song , Zhuo Chen , Chenxi Wang , Xinyu Wang , Kewei Tu , Pengjun Xie , Jingren Zhou , Yong Jiang

Hybrid Group Relative Policy Optimization (Hybrid GRPO) is a reinforcement learning framework that extends Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO) by incorporating empirical multi-sample action…

Machine Learning · Computer Science 2025-02-05 Soham Sane