English
Related papers

Related papers: Future-KL Regularized GRPO: Process-Level Credit A…

200 papers

Recent advancements underscore the significant role of Reinforcement Learning (RL) in enhancing the Chain-of-Thought (CoT) reasoning capabilities of large language models (LLMs). Two prominent RL algorithms, Direct Preference Optimization…

Computer Vision and Pattern Recognition · Computer Science 2025-06-11 Chengzhuo Tong , Ziyu Guo , Renrui Zhang , Wenyu Shan , Xinyu Wei , Zhenghao Xing , Hongsheng Li , Pheng-Ann Heng

Reinforcement learning improves LLM reasoning, but PPO/GRPO typically use fixed clipping and decoding temperature, which makes training brittle and tuning-heavy. We propose Adaptive Group Policy Optimization (AGPO), a critic-free refinement…

Machine Learning · Computer Science 2026-05-21 Miaobo Hu , Shuhao Hu , Bokun Wang , Ruohan Wang , Xin Wang , Xiaobo Guo , Daren Zha , Jun Xiao

It is commonly believed that optimizing the reverse KL divergence results in "mode seeking", while optimizing forward KL results in "mass covering", with the latter being preferred if the goal is to sample from multiple diverse modes. We…

Machine Learning · Computer Science 2025-10-24 Anthony GX-Chen , Jatin Prakash , Jeff Guo , Rob Fergus , Rajesh Ranganath

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for facilitating the self-improvement of large language models (LLMs), particularly in the domain of complex reasoning tasks. However,…

Machine Learning · Computer Science 2025-07-17 Ziru Liu , Cheng Gong , Xinyu Fu , Yaofang Liu , Ran Chen , Shoubo Hu , Suiyun Zhang , Rui Liu , Qingfu Zhang , Dandan Tu

GRPO has emerged as a prominent reinforcement learning algorithm for post-training LLMs. Unlike critic-based methods, GRPO computes advantages by estimating the \emph{value baselines} from group-level statistics, eliminating the need for a…

Reinforcement learning from human feedback (RLHF) is an essential technique for ensuring that large language models (LLMs) are aligned with human values and preferences during the post-training phase. As an effective RLHF approach, group…

Machine Learning · Computer Science 2025-06-18 Zonglin Yang , Zhexuan Gu , Houduo Qi , Yancheng Yuan

Trust region policy optimization (TRPO) is a popular and empirically successful policy search algorithm in Reinforcement Learning (RL) in which a surrogate problem, that restricts consecutive policies to be 'close' to one another, is…

Machine Learning · Computer Science 2019-12-13 Lior Shani , Yonathan Efroni , Shie Mannor

Group Relative Policy Optimization (GRPO) is a standard algorithm for reinforcement learning from verifiable rewards, but its group-mean-centered advantage can fail under binary rewards. The failure mode is gradient starvation: when every…

Machine Learning · Computer Science 2026-05-11 Wenhua Nie , Jianan Wu , Junlin Liu , Ziwei Li , Zheng Lin , Zhang Zijian , Yilong Fan , Haoran Zheng , Jyh-Shing Roger Jang

In recent years, reinforcement learning (RL) has gained increasing attention in control engineering. Especially, policy gradient methods are widely used. In this work, we improve the tracking performance of proximal policy optimization…

Machine Learning · Computer Science 2021-07-21 Jana Mayer , Johannes Westermann , Juan Pedro Gutiérrez H. Muriedas , Uwe Mettin , Alexander Lampe

Reinforcement learning (RL) has emerged as a powerful framework for improving the reasoning capabilities of large language models (LLMs). However, most existing RL approaches rely on sparse outcome rewards, which fail to credit correct…

Machine Learning · Computer Science 2026-01-28 Haolin Liu , Dian Yu , Sidi Lu , Yujun Zhou , Rui Liu , Zhenwen Liang , Haitao Mi , Chen-Yu Wei , Dong Yu

Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a promising framework for enhancing the reasoning capabilities of large language models. However, existing approaches such as GRPO often suffer from zero gradients. This…

Computation and Language · Computer Science 2025-09-09 Shihui Yang , Chengfeng Dou , Peidong Guo , Kai Lu , Qiang Ju , Fei Deng , Rihui Xin

In the post-training of large language models (LLMs), Reinforcement Learning from Human Feedback (RLHF) is an effective approach to achieve generation aligned with human preferences. Direct Preference Optimization (DPO) allows for policy…

Machine Learning · Computer Science 2025-06-16 Motoki Omura , Yasuhiro Fujita , Toshiki Kataoka

Latent reasoning offers a more efficient alternative to explicit reasoning by compressing intermediate reasoning into continuous representations and substantially shortening reasoning chains. However, existing latent reasoning methods…

Machine Learning · Computer Science 2026-05-01 Jingcheng Deng , Zihao Wei , Liang Pang , Junhong Wu , Shicheng Xu , Zenghao Duan , Huawei Shen

Large Language Models (LLMs) can acquire extensive world knowledge through pre-training on large corpora. However, due to exposure to low-quality data, LLMs may exhibit harmful behavior without aligning with human values. The dominant…

Machine Learning · Computer Science 2023-10-11 Tianhao Wu , Banghua Zhu , Ruoyu Zhang , Zhaojin Wen , Kannan Ramchandran , Jiantao Jiao

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

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

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

Large Language Models (LLMs) often generate unnecessarily verbose Chain-of-Thought (CoT) reasoning that increases computational costs and latency without proportional performance gains. In this paper, we propose Fine-grained Group policy…

Machine Learning · Computer Science 2026-03-12 Xinchen Han , Hossam Afifi , Michel Marot , Xilu Wang , Lu Yin

Reinforcement learning (RL) is a key paradigm for post-training large language models (LLMs), but the widely used Group Relative Policy Optimization (GRPO) often suffers from entropy collapse: exploration quickly disappears, policies…

Machine Learning · Computer Science 2026-05-19 Chen Wang , Zhaochun Li , Jionghao Bai , Hexuan Deng , Ge Lan , Yue Wang

Group-relative RL training (GRPO) samples a small group of parallel rollouts for every training prompt and uses their within-group reward spread to compute per-trajectory advantages. In agentic environments each rollout is a long multi-turn…

Machine Learning · Computer Science 2026-05-08 Zhiyuan Zhai , Xin Wang
‹ Prev 1 8 9 10 Next ›