English
Related papers

Related papers: Single-Rollout Hidden-State Dynamics for Training-…

200 papers

Double-machine-learning pipelines for the Average Dose-Response Function rely on kernel-weighted local-linear smoothers, which inherit unbounded functional influence: a single outlier within a kernel window biases the curve across the…

Machine Learning · Statistics 2026-05-04 Eichi Uehara

Reinforcement learning with verifiable rewards (RLVR) is a simple but powerful paradigm for training LLMs: sample a completion, verify it, and update. In practice, however, the verifier is almost never clean--unit tests probe only limited…

Machine Learning · Computer Science 2026-01-09 Ali Rad , Khashayar Filom , Darioush Keivan , Peyman Mohajerin Esfahani , Ehsan Kamalinejad

Reinforcement learning with verifiable rewards (RLVR) enables large language models to acquire slow, multi-step reasoning from sparse final-answer signals. We provide a statistical-physics picture of this emergence. We show that an…

Artificial Intelligence · Computer Science 2026-05-08 Sihan Hu , Xiansheng Cai , Yuan Huang , Zhiyuan Yao , Linfeng Zhang , Pan Zhang , Youjin Deng , Kun Chen

Online reinforcement learning with verifiable rewards (RLVR) turns checkable outcomes into a scalable training signal, but it keeps rollout generation, verifier scoring, and reference-policy evaluations on the optimization path. Static…

Machine Learning · Computer Science 2026-05-05 Yao Shu , Chenxing Wei , Hongbin Lin , Shuang Qiu , Hui Xiong

Test-time scaling has been shown to substantially improve large language models' (LLMs) mathematical reasoning. However, for a large portion of mathematical corpora, especially theorem proving, RLVR's scalability is limited: intermediate…

Computation and Language · Computer Science 2025-11-24 Zhen Wang , Zhifeng Gao , Guolin Ke

Reinforcement learning with verifiable rewards (RLVR) is a practical, scalable way to improve large language models on math, code, and other structured tasks. However, we argue that many headline RLVR gains are not yet well validated…

Reinforcement Learning with Verifiable Rewards (RLVR) has recently demonstrated remarkable potential in enhancing the reasoning capability of Large Reasoning Models (LRMs). However, RLVR often drives the policy toward over-determinism,…

Machine Learning · Computer Science 2026-03-23 Shimin Zhang , Xianwei Chen , Yufan Shen , Ziyuan Ye , Jibin Wu

Previous study suggest that powerful Large Language Models (LLMs) trained with Reinforcement Learning with Verifiable Rewards (RLVR) only refines reasoning path without improving the reasoning capacity in math tasks while…

Computation and Language · Computer Science 2025-05-29 Ran Li , Shimin Di , Yuchen Liu , Chen Jing , Yu Qiu , Lei Chen

Reinforcement Learning with Verifiable Reward (RLVR) has proven effective for training reasoning-oriented large language models, but existing methods largely assume high-resource settings with abundant training data. In low-resource…

Machine Learning · Computer Science 2026-04-21 Zhanyu Liu , Qingguo Hu , Ante Wang , Chenqing Liu , Zhishang Xiang , Hui Li , Delai Qiu , Jinsong Su

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

Reinforcement learning (RL) systems, while achieving remarkable success across various domains, are vulnerable to adversarial attacks. This is especially a concern in vision-based environments where minor manipulations of high-dimensional…

Machine Learning · Computer Science 2025-11-12 Xiaolin Sun , Feidi Liu , Zhengming Ding , ZiZhan Zheng

This paper investigates the role of explicit thinking process in rule-based reinforcement fine-tuning (RFT) for MLLMs. We first propose CLS-RL for MLLM image classification, using verifiable rewards for fine-tuning. Experiments show CLS-RL…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Ming Li , Jike Zhong , Shitian Zhao , Yuxiang Lai , Haoquan Zhang , Wang Bill Zhu , Kaipeng Zhang

Understanding cognitive processes in major depressive disorder (MDD) often relies on behavioral tasks, which are typically analyzed separately, overlooking potential correlations and shared latent structure. To address this limitation, we…

Methodology · Statistics 2026-05-26 Yuan Bian , Yuanjia Wang , Xingche Guo

Reinforcement learning with verifiable rewards (RLVR) has become a key technique for enhancing LLMs' reasoning abilities, yet its data inefficiency remains a major bottleneck. To address this critical yet challenging issue, we present a…

Machine Learning · Computer Science 2026-04-28 Shipeng Li , Zhiqin Yang , Shikun Li , Xiaobo Xia , Hengyu Liu , Xinghua Zhang , Gaode Chen , Dong Fang , Ying Tai , Zhe Peng

Reinforcement learning with verifiable rewards (RLVR) has become a dominant paradigm for improving reasoning in large language models (LLMs), yet the underlying geometry of the resulting parameter trajectories remains underexplored. In this…

Machine Learning · Computer Science 2026-05-21 Zhepei Wei , Xinyu Zhu , Wei-Lin Chen , Chengsong Huang , Jiaxin Huang , Yu Meng

Reinforcement learning with verifiable rewards (RLVR) is effective for training large language models on deterministic outcome reasoning tasks. Prior work shows RLVR works with few prompts, but prompt selection is often based only on…

Machine Learning · Computer Science 2026-05-07 Yujuan Pang , Jiaxin Li , Xin Sheng , Ran Peng , Yong Ma

Data selection is a critical aspect of Reinforcement Learning with Verifiable Rewards (RLVR) for enhancing the reasoning capabilities of large language models (LLMs). Current data selection methods are largely heuristic-based, lacking…

Machine Learning · Computer Science 2026-04-16 Erle Zhu , Dazhi Jiang , Yuan Wang , Xujun Li , Jiale Cheng , Yuxian Gu , Yilin Niu , Aohan Zeng , Jie Tang , Minlie Huang , Hongning Wang

Large language models (LLMs) excel at mathematical reasoning and logical problem-solving. The current popular training paradigms primarily use supervised fine-tuning (SFT) and reinforcement learning (RL) to enhance the models' reasoning…

Machine Learning · Computer Science 2025-08-05 Jack Chen , Fazhong Liu , Naruto Liu , Yuhan Luo , Erqu Qin , Harry Zheng , Tian Dong , Haojin Zhu , Yan Meng , Xiao Wang

While Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a promising post-training paradigm for Large Language Models (LLMs), its dependency on the gold label or domain-specific verifiers limits its scalability to…

Machine Learning · Computer Science 2026-05-12 Xuexiang Wen , Hang Yu , Linchao Zhu , Gaoang Wang

Reinforcement learning (RL) has become a standard paradigm for refining large language models (LLMs) beyond pre-training and instruction tuning. A prominent line of work is RL with verifiable rewards (RLVR), which leverages automatically…

Machine Learning · Computer Science 2025-09-23 Bonan Zhang , Zhongqi Chen , Bowen Song , Qinya Li , Fan Wu , Guihai Chen