English
Related papers

Related papers: DSDR: Dual-Scale Diversity Regularization for Expl…

200 papers

Despite rapid advancements, current text-to-image (T2I) models predominantly rely on a single-step generation paradigm, which struggles with complex semantics and faces diminishing returns from parameter scaling. While recent multi-step…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Hanbo Cheng , Limin Lin , Ruo Zhang , Yicheng Pan , Jun Du

Entropy regularization is a standard technique in reinforcement learning (RL) to enhance exploration, yet it yields negligible effects or even degrades performance in Large Language Models (LLMs). We attribute this failure to the cumulative…

Computation and Language · Computer Science 2026-02-04 Chao Huang , Yujing Lu , Quangang Li , Shenghe Wang , Yan Wang , Yueyang Zhang , Long Xia , Jiashu Zhao , Zhiyuan Sun , Daiting Shi , Tingwen Liu

Deep search agents have proven effective in enhancing LLMs by retrieving external knowledge during multi-step reasoning. However, existing methods often generate a single query for retrieval at each reasoning step, limiting information…

Artificial Intelligence · Computer Science 2026-05-14 Jiabei Liu , Wenyu Mao , Junfei Tan , Chunxu Shen , Lingling Yi , Jiancan Wu , Xiang Wang

The evolution of Large Language Models (LLMs) has catalyzed a paradigm shift from superficial instruction following to rigorous long-horizon reasoning. While Group Relative Policy Optimization (GRPO) has emerged as a pivotal mechanism for…

Artificial Intelligence · Computer Science 2026-01-01 Xuan Xie , Xuan Wang , Wenjie Wang , Shuai Chen , Wei Lin

Recent search-augmented LLMs trained with reinforcement learning (RL) can interleave searching and reasoning for multi-hop reasoning tasks. However, they face two critical failure modes as the accumulating context becomes flooded with both…

Computation and Language · Computer Science 2026-01-14 Kangcheng Luo , Tinglang Wu , Yansong Feng

The double descent (DD) paradox, where over-parameterized models see generalization improve past the interpolation point, remains largely unexplored in the non-stationary domain of Deep Reinforcement Learning (DRL). We present preliminary…

Machine Learning · Computer Science 2025-11-11 Viktor Veselý , Aleksandar Todorov , Matthia Sabatelli

Reinforcement learning (RL) can refine the reasoning abilities of large language models (LLMs), but critically depends on a key prerequisite: the LLM can already generate high-utility reasoning paths with non-negligible probability. For…

Artificial Intelligence · Computer Science 2025-10-30 Tianqianjin Lin , Xi Zhao , Xingyao Zhang , Rujiao Long , Yi Xu , Zhuoren Jiang , Wenbo Su , Bo Zheng

Reinforcement Learning from Verifiable Rewards (RLVR) improves the reasoning abilities of Large Language Models (LLMs) but it struggles with unstable exploration. We propose FR3E (First Return, Entropy-Eliciting Explore), a structured…

Artificial Intelligence · Computer Science 2025-07-10 Tianyu Zheng , Tianshun Xing , Qingshui Gu , Taoran Liang , Xingwei Qu , Xin Zhou , Yizhi Li , Zhoufutu Wen , Chenghua Lin , Wenhao Huang , Qian Liu , Ge Zhang , Zejun Ma

Deep reinforcement learning (DRL) shows promising potential for autonomous driving decision-making. However, DRL demands extensive computational resources to achieve a qualified policy in complex driving scenarios due to its low learning…

Robotics · Computer Science 2024-12-25 Hao Pang , Zhenpo Wang , Guoqiang Li

Recent applications of Reinforcement Learning with Verifiable Rewards (RLVR) to Large Language Models (LLMs) and Vision-Language Models (VLMs) have demonstrated significant success in enhancing reasoning capabilities for complex tasks.…

Computation and Language · Computer Science 2026-02-06 Fanfan Liu , Youyang Yin , Peng Shi , Siqi Yang , Zhixiong Zeng , Haibo Qiu

Reinforcement Learning with Verifiable Rewards (RLVR), primarily driven by the Group Relative Policy Optimization (GRPO) algorithm, is a leading approach for enhancing the reasoning abilities of Large Language Models (LLMs). Despite its…

Machine Learning · Computer Science 2025-10-21 Kangqi Ni , Zhen Tan , Zijie Liu , Pingzhi Li , Tianlong Chen

We consider the problem of sufficient dimensionality reduction (SDR), where the high-dimensional observation is transformed to a low-dimensional sub-space in which the information of the observations regarding the label variable is…

Machine Learning · Computer Science 2018-12-20 Ershad Banijamali , Amir-Hossein Karimi , Ali Ghodsi

Reinforcement learning (RL) has demonstrated potential for enhancing reasoning in large language models (LLMs). However, effective RL training, which requires medium-difficulty training samples, faces two fundamental challenges: Effective…

Machine Learning · Computer Science 2026-05-19 Ru Zhang , Renda Li , Ziyu Ma , Weijie Qiu , Chongyang Tao , Yong Wang , Xiangxiang Chu

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for enhancing reasoning in Large Language Models (LLMs). However, existing reward formulations typically treat exploration and consolidation as a…

Machine Learning · Computer Science 2026-05-15 Wenze Lin , Zhen Yang , Xitai Jiang , Xiaoteng Ma , Gao Huang

Reinforcement learning with verifiable rewards (RLVR) has demonstrated promising potential to enhance the reasoning capabilities of large language models (LLMs) in domains such as mathematics and coding. However, its applications on…

Computation and Language · Computer Science 2026-05-19 Zhonghang Yuan , Zhefan Wang , Fang Hu , Zihong Chen , Jinzhe Li , Gang Li , Jie Ying , Huanjun Kong , Songyang Zhang , Nanqing Dong

Deep Reinforcement Learning (DRL) has achieved remarkable success in sequential decision-making tasks across diverse domains, yet its reliance on black-box neural architectures hinders interpretability, trust, and deployment in high-stakes…

Machine Learning · Computer Science 2025-02-12 Zelei Cheng , Jiahao Yu , Xinyu Xing

Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising paradigm for post-training large language models (LLMs) on complex reasoning tasks. Yet, the conditions under which RLVR yields robust generalization remain…

Machine Learning · Computer Science 2026-03-05 Brian Lu , Hongyu Zhao , Shuo Sun , Hao Peng , Rui Ding , Hongyuan Mei

While inference-time thinking allows Large Language Models (LLMs) to address complex problems, the extended thinking process can be unreliable or inconsistent because of the model's probabilistic nature, especially near its knowledge…

Machine Learning · Computer Science 2025-12-01 Diji Yang , Linda Zeng , Kezhen Chen , Yi Zhang

It is widely recognized that reinforcement learning (RL) fine-tuning of large language models often leads to diversity collapse, where outputs lack variety. Prior work has proposed a range of heuristics to counteract this effect, but these…

Machine Learning · Computer Science 2025-12-12 Jingchu Gai , Guanning Zeng , Huaqing Zhang , Aditi Raghunathan

Reinforcement learning with verifiable rewards (RLVR) succeeds in reasoning tasks (e.g., math and code) by checking the final verifiable answer (i.e., a verifiable dot signal). However, extending this paradigm to open-ended generation is…

Computation and Language · Computer Science 2026-01-27 Yuxin Jiang , Yufei Wang , Qiyuan Zhang , Xingshan Zeng , Liangyou Li , Jierun Chen , Chaofan Tao , Haoli Bai , Lifeng Shang
‹ Prev 1 3 4 5 6 7 10 Next ›