中文
相关论文

相关论文: Length-Unbiased Sequence Policy Optimization: Reve…

200 篇论文

Since the release of Deepseek-R1, reinforcement learning with verifiable rewards (RLVR) has become a central approach for training large language models (LLMs) on reasoning tasks. Recent work has largely focused on modifying loss functions…

机器学习 · 计算机科学 2025-10-03 Weizhe Chen , Sven Koenig , Bistra Dilkina

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for facilitating the self-improvement of large language models (LLMs), particularly in the domain of complex reasoning tasks. However,…

机器学习 · 计算机科学 2025-07-17 Ziru Liu , Cheng Gong , Xinyu Fu , Yaofang Liu , Ran Chen , Shoubo Hu , Suiyun Zhang , Rui Liu , Qingfu Zhang , Dandan Tu

Diffusion large language models (dLLMs) offer a promising route to parallel and efficient text generation, but improving their reasoning ability requires effective post-training. Reinforcement learning with verifiable rewards (RLVR) is a…

计算与语言 · 计算机科学 2026-05-12 Zichao Yu , Shengze Xu , Bingqing Jiang , Wenyi Zhang , Difan Zou

Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capabilities of Large Language Models (LLMs) by leveraging direct outcome verification instead of learned reward models. Building on this paradigm, Group…

Reinforcement Learning with Verifiable Rewards (RLVR) has achieved substantial gains in single-attempt accuracy (Pass@1) on reasoning tasks, yet often suffers from reduced multi-sample coverage (Pass@K), indicating diversity collapse. We…

机器学习 · 计算机科学 2026-05-04 Anamika Lochab , Bolian Li , Ruqi Zhang

Improving and understanding the training dynamics and reasoning of Large Language Models (LLMs) has become essential for their deployment in AI-based security tools, such as software vulnerability detection. In this work, we present an…

密码学与安全 · 计算机科学 2025-07-08 Marco Simoni , Aleksandar Fontana , Giulio Rossolini , Andrea Saracino

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…

机器学习 · 计算机科学 2025-10-21 Kangqi Ni , Zhen Tan , Zijie Liu , Pingzhi Li , Tianlong Chen

Reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving reasoning language models on tasks such as mathematics, coding, and scientific question answering. However, widely used group-relative…

计算与语言 · 计算机科学 2026-05-29 Redacted by arXiv

When applying reinforcement learning--typically through GRPO--to large vision-language model reasoning struggles to effectively scale reasoning length or generates verbose outputs across all tasks with only marginal gains in accuracy. To…

计算与语言 · 计算机科学 2025-10-24 Wenyi Xiao , Leilei Gan

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach for improving the reasoning abilities of large language models (LLMs). The Group Relative Policy Optimization (GRPO) family has demonstrated strong…

计算与语言 · 计算机科学 2025-11-10 Chenxi Liu , Junjie Liang , Yuqi Jia , Bochuan Cao , Yang Bai , Heng Huang , Xun Chen

Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capacity of Large Language Models (LLMs). However, RLVR solely relies on final answers as outcome rewards, neglecting the correctness of…

机器学习 · 计算机科学 2026-03-12 Sijia Cui , Pengyu Cheng , Jiajun Song , Yongbo Gai , Guojun Zhang , Zhechao Yu , Jianhe Lin , Xiaoxi Jiang , Guanjun Jiang

Multimodal large language models (MLLMs) have shown promising capabilities in reasoning tasks, yet still struggle with complex problems requiring explicit self-reflection and self-correction, especially compared to their unimodal text-based…

Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capability of large language models (LLMs), enabling autonomous agents that can conduct effective multi-turn and tool-integrated reasoning. While instructions…

机器学习 · 计算机科学 2026-02-03 Han Zhou , Xingchen Wan , Ivan Vulić , Anna Korhonen

Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated notable success in enhancing the reasoning performance of large language models (LLMs). However, recent studies reveal that while current RLVR methods improve sampling…

人工智能 · 计算机科学 2026-05-08 Yang Xu , Kun Yao , Yiming Deng , Zheng Fang , Kai Ming Ting , Ming Pang

As a key component of large language model (LLM) post-training, Reinforcement Learning from Verifiable Rewards (RLVR) has substantially improved reasoning performance. However, existing RLVR algorithms exhibit distinct stability issues:…

计算与语言 · 计算机科学 2026-04-13 Kun Yang , Zikang chen , Yanmeng Wang , Zhigen Li , Ning Cheng , Shaojun Wang , Jing Xiao

Recently, online Reinforcement Learning with Verifiable Rewards (RLVR) has become a key paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing methods typically treat all training samples…

人工智能 · 计算机科学 2025-09-30 Shijie Zhang , Guohao Sun , Kevin Zhang , Xiang Guo , Rujun Guo

Reinforcement Learning with Verifiable Rewards (RLVR) has markedly enhanced the reasoning abilities of large language models (LLMs). Its success, however, largely depends on strong base models with rich world knowledge, yielding only modest…

人工智能 · 计算机科学 2025-08-19 Yongxin Guo , Wenbo Deng , Zhenglin Cheng , Xiaoying Tang

Reinforcement learning with verifiable rewards (RLVR) has become a standard approach for large language models (LLMs) post-training to incentivize reasoning capacity. Among existing recipes, group-based policy gradient is prevalent, which…

Reasoning language models have shown an uncanny ability to improve performance at test-time by ``thinking longer''-that is, by generating longer chain-of-thought sequences and hence using more compute. However, the length of their…

计算与语言 · 计算机科学 2025-10-06 Pranjal Aggarwal , Sean Welleck

We propose VL Norm (Variance-reduced Length-dependent Normalization), a simple yet effective loss aggregation method tailored to the characteristic of dynamic generation lengths in Reinforcement Learning with Verifiable Rewards (RLVR).…

机器学习 · 计算机科学 2025-10-14 Zhiyuan He , Xufang Luo , Yike Zhang , Yuqing Yang , Lili Qiu
‹ 上一页 1 2 3 10 下一页 ›