English
Related papers

Related papers: Beyond Binary: Turning Partial Success into Dense …

200 papers

The goal of robust constrained reinforcement learning (RL) is to optimize an agent's performance under the worst-case model uncertainty while satisfying safety or resource constraints. In this paper, we demonstrate that strong duality does…

Machine Learning · Computer Science 2025-09-23 Shaocong Ma , Ziyi Chen , Yi Zhou , Heng Huang

Off-policy updates are inevitable in reinforcement learning (RL) for large language models (LLMs) due to rollout staleness from asynchronous training and mismatches between training and inference engines. Naive importance sampling gives an…

Machine Learning · Computer Science 2026-05-11 Guobin Shen , Chenxiao Zhao , Xiang Cheng , Lei Huang , Xing Yu

Recent advances demonstrate that reinforcement learning with verifiable rewards (RLVR) significantly enhances the reasoning capabilities of large language models (LLMs). However, standard RLVR faces challenges with reward sparsity, where…

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

Policy-based reinforcement learning currently plays an important role in improving LLMs on mathematical reasoning tasks. However, existing rollout-based reinforcement learning methods (GRPO, DAPO, GSPO, etc.) fail to explicitly consider…

Machine Learning · Computer Science 2025-09-25 Guochao Jiang , Wenfeng Feng , Guofeng Quan , Chuzhan Hao , Yuewei Zhang , Guohua Liu , Hao Wang

We present Future-KL Influenced Policy Optimization (FIPO), a reinforcement learning algorithm designed to overcome reasoning bottlenecks in large language models. While GRPO style training scales effectively, it typically relies on…

Machine Learning · Computer Science 2026-04-01 Chiyu Ma , Shuo Yang , Kexin Huang , Jinda Lu , Haoming Meng , Shangshang Wang , Bolin Ding , Soroush Vosoughi , Guoyin Wang , Jingren Zhou

We propose Process-Aware Policy Optimization (PAPO), a method that integrates process-level evaluation into Group Relative Policy Optimization (GRPO) through decoupled advantage normalization, to address two limitations of existing reward…

Artificial Intelligence · Computer Science 2026-04-06 Zelin Tan , Zhouliang Yu , Bohan Lin , Zijie Geng , Hejia Geng , Yudong Zhang , Mulei Zhang , Yang Chen , Shuyue Hu , Zhenfei Yin , Chen Zhang , Lei Bai

State-of-the-art reasoning models utilize long chain-of-thought (CoT) to solve increasingly complex problems using more test-time computation. In this work, we explore a long CoT setting where the model makes up to K successive attempts at…

Machine Learning · Computer Science 2026-04-21 Muhammed Emrullah Ildiz , Halil Alperen Gozeten , Ege Onur Taga , Samet Oymak

Generating accurate and executable code using Large Language Models (LLMs) remains a significant challenge for underrepresented programming languages, such as Prolog and Lisp, due to the scarcity of public training data compared to…

Machine Learning · Computer Science 2026-05-26 Federico Pennino , Bianca Raimondi , Massimo Rondelli , Andrea Gurioli , Maurizio Gabbrielli

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

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…

In this paper, we propose AlphaGRPO, a novel framework that applies Group Relative Policy Optimization (GRPO) to AR-Diffusion Unified Multimodal Models (UMMs) to enhance multimodal generation capabilities without an additional cold-start…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Runhui Huang , Jie Wu , Rui Yang , Zhe Liu , Hengshuang Zhao

Reinforcement learning with verifiable rewards has driven recent advances in LLM post-training, in particular for reasoning. Policy optimization algorithms generate a number of responses for a given prompt and then effectively weight the…

Machine Learning · Computer Science 2026-02-12 Reinhard Heckel , Mahdi Soltanolkotabi , Christos Thramboulidis

While Reinforcement Learning with Verifiable Rewards (RLVR) enhances complex reasoning in LLMs, current methods struggle to balance exploration and exploitation. This leads to critical issues like inaccurate credit assignment for…

Machine Learning · Computer Science 2025-10-13 Junxi Yin , Haisen Luo , Zhenyu Li , Yihua Liu , Dan Liu , Zequn Li , Xiaohang Xu

Reinforcement learning (RL) post-training is crucial for aligning generative models with human preferences, but its prohibitive computational cost remains a major barrier to widespread adoption. We introduce \textbf{TreeGRPO}, a novel RL…

Machine Learning · Computer Science 2025-12-10 Zheng Ding , Weirui Ye

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

Reinforcement learning with verifiable rewards (RLVR) enhances the reasoning of large language models (LLMs), but standard RLVR often depends on human-annotated answers or carefully curated reward specifications. In machine-checkable…

Artificial Intelligence · Computer Science 2026-04-29 Xinjie Chen , Biao Fu , Jing Wu , Guoxin Chen , Xinggao Liu , Dayiheng Liu , Minpeng Liao

Inspired by the success of DeepSeek-R1, we explore the potential of rule-based reinforcement learning (RL) in MLLM post-training for perception policy learning. While promising, our initial experiments reveal that incorporating a thinking…

Computer Vision and Pattern Recognition · Computer Science 2025-04-11 En Yu , Kangheng Lin , Liang Zhao , Jisheng Yin , Yana Wei , Yuang Peng , Haoran Wei , Jianjian Sun , Chunrui Han , Zheng Ge , Xiangyu Zhang , Daxin Jiang , Jingyu Wang , Wenbing Tao

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

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for complex reasoning tasks with clear correctness signals such as math and coding. However, extending it to real-world reasoning tasks is challenging, as evaluation…

Machine Learning · Computer Science 2025-10-06 Anisha Gunjal , Anthony Wang , Elaine Lau , Vaskar Nath , Yunzhong He , Bing Liu , Sean Hendryx