English
Related papers

Related papers: GAPO: Robust Advantage Estimation for Real-World C…

200 papers

Diffusion large language models (dLLMs), which offer a promising alternative to traditional autoregressive LLMs, have recently shown strong results in pretraining. However, due to their lack of tractable sequence-level likelihoods, they…

Machine Learning · Computer Science 2026-02-03 Anthony Zhan

Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), yet its efficacy is primarily confined to domains with verifiable ground truths. Extending GRPO to open-domain…

Machine Learning · Computer Science 2026-04-14 Yang Zhao , Hepeng Wang , Xiao Ding , Yangou Ouyang , Bibo Cai , Kai Xiong , Jinglong Gao , Zhouhao Sun , Li Du , Bing Qin , Ting Liu

Training large language models (LLMs) as interactive agents for controlling graphical user interfaces (GUIs) presents a unique challenge to optimize long-horizon action sequences with multimodal feedback from complex environments. While…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Fanbin Lu , Zhisheng Zhong , Shu Liu , Chi-Wing Fu , Jiaya Jia

Recent works have demonstrated the effectiveness of reinforcement learning (RL)-based post-training for enhancing the reasoning capabilities of large language models (LLMs). In particular, Group Relative Policy Optimization (GRPO) has shown…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Jinyoung Park , Jeehye Na , Jinyoung Kim , Hyunwoo J. Kim

Off-policy reinforcement learning (RL) for large language models (LLMs) is attracting growing interest, driven by practical constraints in real-world applications, the complexity of LLM-RL infrastructure, and the need for further…

Machine Learning · Computer Science 2026-03-03 Chaorui Yao , Yanxi Chen , Yuchang Sun , Yushuo Chen , Wenhao Zhang , Xuchen Pan , Yaliang Li , Bolin Ding

As a key component of large language model (LLM) post-training, Reinforcement Learning from Verifiable Rewards (RLVR) has substantially improved reasoning performance. However, existing RLVR algorithms exhibit distinct stability issues:…

Computation and Language · Computer Science 2026-04-13 Kun Yang , Zikang chen , Yanmeng Wang , Zhigen Li , Ning Cheng , Shaojun Wang , Jing Xiao

On-policy reinforcement learning (RL), particularly Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), has become the dominant paradigm for fine-tuning large language models (LLMs). While policy ratio clipping…

Machine Learning · Computer Science 2026-01-08 Yu Luo , Shuo Han , Yihan Hu , Dong Li , Jianye Hao

This paper introduces Group Sequence Policy Optimization (GSPO), our stable, efficient, and performant reinforcement learning algorithm for training large language models. Unlike previous algorithms that adopt token-level importance ratios,…

Machine Learning · Computer Science 2025-07-29 Chujie Zheng , Shixuan Liu , Mingze Li , Xiong-Hui Chen , Bowen Yu , Chang Gao , Kai Dang , Yuqiong Liu , Rui Men , An Yang , Jingren Zhou , Junyang Lin

This study presents a systematic comparison of three Reinforcement Learning (RL) algorithms (PPO, GRPO, and DAPO) for improving complex reasoning in large language models (LLMs). Our main contribution is a controlled transfer-learning…

Artificial Intelligence · Computer Science 2025-12-09 Yongsheng Lian

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…

The enhancement of reasoning capabilities in large language models (LLMs) has garnered significant attention, with supervised fine-tuning (SFT) and reinforcement learning emerging as dominant paradigms. While recent studies recognize the…

Artificial Intelligence · Computer Science 2026-03-17 Zhijie Wang

RL-based post-training with GRPO is widely used to improve large language models on individual reasoning tasks. However, real-world deployment requires reliable performance across diverse tasks. A straightforward multi-task adaptation of…

Reinforcement Learning (RL) can directly enhance the reasoning capabilities of large language models without extensive reliance on Supervised Fine-Tuning (SFT). In this work, we revisit the traditional Policy Gradient (PG) mechanism and…

Machine Learning · Computer Science 2026-02-04 Xiangxiang Chu , Hailang Huang , Xiao Zhang , Fei Wei , Yong Wang

The success of Deepseek-R1 has drawn the LLM community's attention to reinforcement learning (RL) methods like GRPO. However, such rule-based 0/1 outcome reward methods lack the capability to regulate the intermediate reasoning processes…

Artificial Intelligence · Computer Science 2025-05-26 Muzhi Dai , Shixuan Liu , Qingyi Si

Diffusion large language models (dLLMs) offer a promising route to parallel and efficient text generation, but improving their reasoning ability requires effective post-training. Reinforcement learning with verifiable rewards (RLVR) is a…

Computation and Language · Computer Science 2026-05-12 Zichao Yu , Shengze Xu , Bingqing Jiang , Wenyi Zhang , Difan Zou

Group Relative Policy Optimization (GRPO) has emerged as the de facto Reinforcement Learning (RL) objective driving recent advancements in Multimodal Large Language Models. However, extending this success to open-source multimodal…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Wenbo Hu , Xin Chen , Yan Gao-Tian , Yihe Deng , Nanyun Peng , Kai-Wei Chang

This paper introduces Completion Pruning Policy Optimization (CPPO) to accelerate the training of reasoning models based on Group Relative Policy Optimization (GRPO). GRPO, while effective, incurs high training costs due to the need to…

Artificial Intelligence · Computer Science 2025-11-11 Zhihang Lin , Mingbao Lin , Yuan Xie , Rongrong Ji

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

Aligning large-scale vision-language models (VLMs) for complex reasoning via reinforcement learning is often hampered by the limitations of existing policy optimization algorithms, such as static training schedules and the rigid, uniform…

Artificial Intelligence · Computer Science 2025-10-02 Yunhao Wang , Ziting Li , Shuai Chen , Tao Liu , Chao Song , Junjie Jiang , Jian Zhu , Peng Gao , Bin Qin

Despite the efficacy of Direct Preference Optimization (DPO) in aligning Large Language Models (LLMs), reward hacking remains a pivotal challenge. This issue emerges when LLMs excessively reduce the probability of rejected completions to…

Computation and Language · Computer Science 2025-08-26 Chenxu Yang , Ruipeng Jia , Mingyu Zheng , Naibin Gu , Zheng Lin , Siyuan Chen , Weichong Yin , Hua Wu , Weiping Wang