中文
相关论文

相关论文: VI-CuRL: Stabilizing Verifier-Independent RL Reaso…

200 篇论文

While large language models (LLMs) have demonstrated strong performance on factoid question answering, they are still prone to hallucination and untruthful responses, particularly when tasks demand information outside their parametric…

Using Reinforcement Learning with Verifiable Rewards (RLVR) to optimize Large Language Models (LLMs) can be conceptualized as progressively editing a query's `Reasoning Tree'. This process involves exploring nodes (tokens) and dynamically…

人工智能 · 计算机科学 2026-04-28 Hong Wang , Zhezheng Hao , Jian Luo , Chenxing Wei , Yao Shu , Lei Liu , Qiang Lin , Hande Dong , Jiawei Chen

Risk-sensitive reinforcement learning (RL) aims to optimize policies that balance the expected reward and risk. In this paper, we present a novel risk-sensitive RL framework that employs an Iterated Conditional Value-at-Risk (CVaR)…

机器学习 · 计算机科学 2023-12-05 Yu Chen , Yihan Du , Pihe Hu , Siwei Wang , Desheng Wu , Longbo Huang

Reinforcement learning (RL) has proven effective for fine-tuning large language models (LLMs), significantly enhancing their reasoning abilities in domains such as mathematics and code generation. A crucial factor influencing RL fine-tuning…

Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training method for improving the reasoning abilities of Large Language Models (LLMs). However, existing methods mainly apply uniform optimization…

计算与语言 · 计算机科学 2026-05-18 Jiakang Wang , Runze Liu , Fuzheng Zhang , Xiu Li , Guorui Zhou , Ling Pan

Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced reasoning capabilities in Large Language Models. However, adapting RLVR to multimodal domains suffers from a critical \textit{perception-reasoning decoupling}.…

人工智能 · 计算机科学 2026-01-13 Shujian Gao , Yuan Wang , Jiangtao Yan , Zuxuan Wu , Yu-Gang Jiang

While Large Language Models (LLMs) excel at code generation by learning from vast code corpora, a fundamental semantic gap remains between their training on textual patterns and the goal of functional correctness, which is governed by…

While Reinforcement Learning for Verifiable Rewards (RLVR) is powerful for training large reasoning models, its training dynamics harbor a critical challenge: RL overfitting, where models gain training rewards but lose generalization. Our…

人工智能 · 计算机科学 2025-11-07 Zeng Zhiyuan , Jiashuo Liu , Zhangyue Yin , Ge Zhang , Wenhao Huang , Xipeng Qiu

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for enhancing Large Language Models (LLMs) on complex reasoning tasks. However, existing methods suffer from an exploration dilemma: the sharply peaked initial…

人工智能 · 计算机科学 2025-09-30 Yuhua Jiang , Jiawei Huang , Yufeng Yuan , Xin Mao , Yu Yue , Qianchuan Zhao , Lin Yan

Reinforcement Fine-Tuning (RFT) with verifiable rewards has advanced large language models but remains underexplored for Vision-Language (VL) models. The Vision-Language Reward Model (VL-RM) is key to aligning VL models by providing…

计算与语言 · 计算机科学 2025-06-18 Jipeng Zhang , Kehao Miao , Renjie Pi , Zhaowei Wang , Runtao Liu , Rui Pan , Tong Zhang

We show that reinforcement learning with verifiable rewards (RLVR) can elicit strong mathematical reasoning in certain language models even with spurious rewards that have little, no, or even negative correlation with the correct answer.…

Reinforcement Learning with Verifiable Rewards (RLVR) replaces costly human labeling with automated verifiers. To reduce verifier hacking, many RLVR systems binarize rewards to $\{0,1\}$, but imperfect verifiers inevitably introduce…

机器学习 · 计算机科学 2026-05-25 Xin-Qiang Cai , Wei Wang , Feng Liu , Tongliang Liu , Gang Niu , Masashi Sugiyama

Reinforcement learning with verifiable rewards (RLVR) has been shown to enhance the reasoning capabilities of large language models (LLMs), enabling the development of large reasoning models (LRMs). However, LRMs such as DeepSeek-R1 and…

人工智能 · 计算机科学 2025-11-13 Yuhao Wang , Xiaopeng Li , Cheng Gong , Ziru Liu , Suiyun Zhang , Rui Liu , Xiangyu Zhao

Context or prompt-level reweighting has emerged as a central algorithmic lever in Reinforcement Learning with Verified Rewards (RLVR) for improving the reasoning capability of large language models, yet the principle determining what…

机器学习 · 计算机科学 2026-05-26 Ke Sun , Yizhou Zhao , Jiayi Xin , Qi Long , Weijie Su

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…

机器学习 · 计算机科学 2026-01-09 Ali Rad , Khashayar Filom , Darioush Keivan , Peyman Mohajerin Esfahani , Ehsan Kamalinejad

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of LLMs. Existing research has predominantly concentrated on isolated reasoning domains such as mathematical…

人工智能 · 计算机科学 2025-07-24 Yu Li , Zhuoshi Pan , Honglin Lin , Mengyuan Sun , Conghui He , Lijun Wu

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) for multimodal large language models (MLLMs) have mainly focused on improving final answer correctness and strengthening visual grounding. However, a critical…

计算机视觉与模式识别 · 计算机科学 2026-03-30 Jinda Lu , Junkang Wu , Jinghan Li , Kexin Huang , Shuo Yang , Mingzhu Chen , Jiancan Wu , Kuien Liu , Xiang Wang

Zero Reinforcement Learning (Zero-RL) has proven to be an effective approach for enhancing the reasoning capabilities of large language models (LLMs) by directly applying reinforcement learning with verifiable rewards on pretrained models,…

人工智能 · 计算机科学 2025-10-30 Yuyuan Zeng , Yufei Huang , Can Xu , Qingfeng Sun , Jianfeng Yan , Guanghui Xu , Tao Yang , Fengzong Lian

Reinforcement learning is critical to improving large reasoning models, but its success relies heavily on verifiable rewards (RLVR), making it hard to use in open-ended domains where correctness is ambiguous and cannot be verified.…

人工智能 · 计算机科学 2026-05-12 Yifan Wang , Bolian Li , David Cho , Ruqi Zhang , Fanping Sui , Ananth Grama

Video diffusion models have made rapid progress in perceptual realism and temporal coherence, but they remain primarily optimized for plausible generation rather than verifiable reasoning. This limitation is especially pronounced in tasks…

计算机视觉与模式识别 · 计算机科学 2026-05-18 Tinghui Zhu , Sheng Zhang , James Y. Huang , Selena Song , Xiaofei Wen , Yuankai Li , Hoifung Poon , Muhao Chen