English
Related papers

Related papers: Correct Answers from Sound Reasoning: Verifiable P…

200 papers

Test-time scaling has proven effective in further enhancing the performance of pretrained Large Language Models (LLMs). However, mainstream post-training methods (i.e., reinforcement learning (RL) with chain-of-thought (CoT) reasoning)…

Machine Learning · Computer Science 2025-08-19 Yuyang Xu , Yi Cheng , Haochao Ying , Zhuoyun Du , Renjun Hu , Xing Shi , Wei Lin , Jian Wu

Applying reinforcement learning to improve factual accuracy in knowledge-intensive question answering faces a reward design dilemma. Response-level rewards provide only coarse supervision and cannot distinguish correct from incorrect…

Computation and Language · Computer Science 2026-05-29 Shicheng Fan , Haochang Hao , Dehai Min , Weihao Liu , Philip S. Yu , Lu Cheng

Reinforcement learning with verifiable rewards has significantly advanced reasoning in large language models (LLMs), but such signals remain coarse, offering only binary correctness feedback. This limitation often results in inefficiencies,…

Machine Learning · Computer Science 2026-04-20 Peixuan Han , Adit Krishnan , Gerald Friedland , Jiaxuan You , Chris Kong

Large language models (LLMs) increasingly rely on reinforcement learning (RL) to enhance their reasoning capabilities through feedback. A critical challenge is verifying the consistency of model-generated responses and reference answers,…

Artificial Intelligence · Computer Science 2025-07-29 Xuzhao Li , Xuchen Li , Shiyu Hu , Yongzhen Guo , Wentao Zhang

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…

Recent studies on post-training large language models (LLMs) for reasoning through reinforcement learning (RL) typically focus on tasks that can be accurately verified and rewarded, such as solving math problems. In contrast, our research…

Computation and Language · Computer Science 2025-05-29 Ang Lv , Ruobing Xie , Xingwu Sun , Zhanhui Kang , Rui Yan

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

Reinforcement learning with verifiable rewards (RLVR) is a promising approach for training language models (LMs) on reasoning tasks that elicit emergent long chains of thought (CoTs). Unlike supervised learning, it updates the model using…

Computation and Language · Computer Science 2025-10-28 Xinyu Zhu , Mengzhou Xia , Zhepei Wei , Wei-Lin Chen , Danqi Chen , Yu Meng

Reinforcement learning with verifiable rewards (RLVR) for Large Reasoning Models hinges on baseline estimation for variance reduction, but existing approaches pay a heavy price: PPO requires a policy-model scale critic, while GRPO needs…

Machine Learning · Computer Science 2026-05-12 Yunho Choi , Jongwon Lim , Woojin Ahn , Minjae Oh , Jeonghoon Shim , Yohan Jo

Can reinforcement learning with hard, verifiable rewards teach a compact language model to reason about physics, or does it primarily learn to pattern-match toward correct answers? We study this question by training a 1.5B-parameter…

Artificial Intelligence · Computer Science 2026-03-05 Tarjei Paule Hage , Markus J. Buehler

Reliable spatial reasoning remains a core bottleneck for vision-language models (VLMs). Existing mainstream training paradigms for spatial reasoning largely rely on outcome alignment or process imitation, lacking explicit constraints on the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Jiangyang Li , Cong Wan , Changjie Wu , Songlin Dong , Lingjun Zhang , Linzhe Shi , Xu Wang , Zhiheng Ma , Hang Zhang , Mu Xu , Yihong Gong

Language models trained with reinforcement learning (RL) can engage in reward hacking--the exploitation of unintended strategies for high reward--without revealing this behavior in their chain-of-thought reasoning. This makes the detection…

Computation and Language · Computer Science 2025-07-15 Miles Turpin , Andy Arditi , Marvin Li , Joe Benton , Julian Michael

In this work, we propose a novel method named \textbf{Auto}mated \textbf{P}rocess-\textbf{S}upervised \textbf{V}erifier (\textbf{\textsc{AutoPSV}}) to enhance the reasoning capabilities of large language models (LLMs) by automatically…

Computation and Language · Computer Science 2024-10-25 Jianqiao Lu , Zhiyang Dou , Hongru Wang , Zeyu Cao , Jianbo Dai , Yingjia Wan , Zhijiang Guo

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

Reasoning has substantially improved the performance of large language models (LLMs) on complicated tasks. Central to the current reasoning studies, Process Reward Models (PRMs) offer a fine-grained evaluation of intermediate reasoning…

Machine Learning · Computer Science 2025-11-05 Qi Cao , Ruiyi Wang , Ruiyi Zhang , Sai Ashish Somayajula , Pengtao Xie

Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising approach for training reasoning language models (RLMs) by leveraging supervision from verifiers. Although verifier implementation is easier than solution…

Artificial Intelligence · Computer Science 2026-02-24 Andre He , Nathaniel Weir , Kaj Bostrom , Allen Nie , Darion Cassel , Sam Bayless , Huzefa Rangwala

Reinforcement Learning from Verifiable Rewards (RLVR) has recently shown that large language models (LLMs) can develop their own reasoning without direct supervision. However, applications in the medical domain, specifically for question…

Machine Learning · Computer Science 2025-09-22 Mirza Farhan Bin Tarek , Rahmatollah Beheshti

Large Language Models (LLMs) often struggle with problems that require multi-step reasoning. For small-scale open-source models, Reinforcement Learning with Verifiable Rewards (RLVR) fails when correct solutions are rarely sampled even…

Computation and Language · Computer Science 2026-03-02 Yihe Deng , I-Hung Hsu , Jun Yan , Zifeng Wang , Rujun Han , Gufeng Zhang , Yanfei Chen , Wei Wang , Tomas Pfister , Chen-Yu Lee

Large reasoning models (LRMs) have recently shown promise in solving complex math problems when optimized with Reinforcement Learning (RL). But conventional approaches rely on outcome-only rewards that provide sparse feedback, resulting in…

Machine Learning · Computer Science 2025-08-01 Tao He , Rongchuan Mu , Lizi Liao , Yixin Cao , Ming Liu , Bing Qin