English
Related papers

Related papers: Internalizing Outcome Supervision into Process Sup…

200 papers

Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that get correct answers by chance. We observe that better…

Machine Learning · Computer Science 2026-03-11 Tiehua Mei , Minxuan Lv , Leiyu Pan , Zhenpeng Su , Hongru Hou , Hengrui Chen , Ao Xu , Deqing Yang

The development of autonomous agents for complex, long-horizon tasks is a central goal in AI. However, dominant training paradigms face a critical limitation: reinforcement learning (RL) methods that optimize solely for final task success…

Machine Learning · Computer Science 2025-07-31 Zijing Zhang , Ziyang Chen , Mingxiao Li , Zhaopeng Tu , Xiaolong Li

Large language models excel at short-horizon reasoning tasks, but performance drops as reasoning horizon lengths increase. Existing approaches to combat this rely on inference-time scaffolding or costly step-level supervision, neither of…

Recent advancements in large language models (LLMs) have been driven by their emergent reasoning capabilities, particularly through long chain-of-thought (CoT) prompting, which enables thorough exploration and deliberation. Despite these…

Computation and Language · Computer Science 2026-04-09 Junnan Liu , Hongwei Liu , Songyang Zhang , Kai Chen

Reinforcement learning has emerged as a powerful paradigm for post-training large language models (LLMs) to improve reasoning. Approaches like Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with Verifiable…

Machine Learning · Computer Science 2025-06-26 Yanzhi Zhang , Zhaoxi Zhang , Haoxiang Guan , Yilin Cheng , Yitong Duan , Chen Wang , Yue Wang , Shuxin Zheng , Jiyan He

Reinforcement learning offers the promise of automating the acquisition of complex behavioral skills. However, compared to commonly used and well-understood supervised learning methods, reinforcement learning algorithms can be brittle,…

Machine Learning · Computer Science 2020-01-01 Aviral Kumar , Xue Bin Peng , Sergey Levine

Reasoning-centric video object segmentation is an inherently complex task: the query often refers to dynamics, causality, and temporal interactions, rather than static appearances. Yet existing solutions generally collapse these factors…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Yifan Li , Yingda Yin , Lingting Zhu , Weikai Chen , Shengju Qian , Xin Wang , Yanwei Fu

Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement learning (RL) focused on reasoning capabilities. However,…

Artificial Intelligence · Computer Science 2025-11-12 Qianxi He , Qingyu Ren , Shanzhe Lei , Xuhong Wang , Yingchun Wang

While reinforcement learning (RL) demonstrated remarkable success in enhancing the reasoning capabilities of language models, the training dynamics of RL in LLMs remain unclear. In this work, we provide an explanation of the RL training…

Machine Learning · Computer Science 2025-09-30 Xingwu Chen , Tianle Li , Difan Zou

Reasoning is a hallmark of human intelligence, enabling adaptive decision-making in complex and unfamiliar scenarios. In contrast, machine intelligence remains bound to training data, lacking the ability to dynamically refine solutions at…

Computer Vision and Pattern Recognition · Computer Science 2025-06-30 Shaheer U. Saeed , Yipei Wang , Veeru Kasivisvanathan , Brian R. Davidson , Matthew J. Clarkson , Yipeng Hu , Daniel C. Alexander

Training language models to produce both correct answers and sound reasoning remains an open challenge. Reinforcement learning with verifiable rewards typically optimizes only final outcomes, which can lead to a failure mode where task…

Computation and Language · Computer Science 2026-05-14 Kyuyoung Kim , Kevin Wang , Yunfei Xie , Peiyang Xu , Peiyao Sheng , Chen Wei , Zhangyang Wang , Jinwoo Shin , Pramod Viswanath , Sewoong Oh

Recent successes of reinforcement learning (RL) in training large reasoning models motivate the question of whether self-training - the process where a model learns from its own judgments - can be sustained within RL. In this work, we study…

Machine Learning · Computer Science 2025-10-10 Sheikh Shafayat , Fahim Tajwar , Ruslan Salakhutdinov , Jeff Schneider , Andrea Zanette

Instruction-driven image editing with unified multimodal generative models has advanced rapidly, yet their underlying visual reasoning remains limited, leading to suboptimal performance on reasoning-centric edits. Reinforcement learning…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Hengjia Li , Liming Jiang , Qing Yan , Yizhi Song , Hao Kang , Zichuan Liu , Xin Lu , Boxi Wu , Deng Cai

Quadratic programming is a workhorse of modern nonlinear optimization, control, and data science. Although regularized methods offer convergence guarantees under minimal assumptions on the problem data, they can exhibit the slow…

Optimization and Control · Mathematics 2026-05-18 Jeremy Bertoncini , Alberto De Marchi , Matthias Gerdts , Simon Gottschalk

Meta-learning algorithms use past experience to learn to quickly solve new tasks. In the context of reinforcement learning, meta-learning algorithms acquire reinforcement learning procedures to solve new problems more efficiently by…

Machine Learning · Computer Science 2020-05-01 Abhishek Gupta , Benjamin Eysenbach , Chelsea Finn , Sergey Levine

Recently, reinforcement learning~(RL) has become an important approach for improving the capabilities of large language models~(LLMs). In particular, reinforcement learning from verifiable rewards~(RLVR) has emerged as a promising paradigm…

Machine Learning · Computer Science 2026-03-26 Fei Bai , Zhipeng Chen , Chuan Hao , Ming Yang , Ran Tao , Bryan Dai , Wayne Xin Zhao , Jian Yang , Hongteng Xu

Despite significant progress, Vision-Language Models (VLMs) still struggle with complex visual reasoning, where multi-step dependencies cause early errors to cascade through the reasoning chain. Existing post-training paradigms are limited:…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Yanbei Jiang , Chao Lei , Yihao Ding , Krista Ehinger , Jey Han Lau

Reinforcement learning with verifiable rewards (RLVR) has become central to post-training reasoning models, yet a key limitation of existing studies is their narrow view of the reasoning space: difficulty is treated as reasoning depth…

Computation and Language · Computer Science 2026-05-27 Yihua Zhu , Qianying Liu , Fei Cheng , Jiaxin Wang , Akiko Aizawa , Sadao Kurohashi , Hidetoshi Shimodaira

In the last decade, Deep Reinforcement Learning has evolved into a powerful tool for complex sequential decision-making problems. It combines deep learning's proficiency in processing rich input signals with reinforcement learning's…

Machine Learning · Computer Science 2024-12-11 Julien Roy

The development of reasoning capabilities represents a critical frontier in large language models (LLMs) research, where reinforcement learning (RL) and process reward models (PRMs) have emerged as predominant methodological frameworks.…

Artificial Intelligence · Computer Science 2025-12-09 Zhangying Feng , Qianglong Chen , Ning Lu , Yongqian Li , Siqi Cheng , Shuangmu Peng , Duyu Tang , Shengcai Liu , Zhirui Zhang