English
Related papers

Related papers: Diagnosing and Mitigating System Bias in Self-Rewa…

200 papers

Outcome-reward reinforcement learning (RL) is a common and increasingly significant way to refine the step-by-step reasoning of multimodal large language models (MLLMs). In the multiple-choice setting - a dominant format for multimodal…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Jiahao Wang , Weiye Xu , Aijun Yang , Wengang Zhou , Lewei Lu , Houqiang Li , Xiaohua Wang , Jinguo Zhu

While reinforcement learning has advanced the reasoning abilities of Large Language Models (LLMs), these gains are largely confined to English, creating a significant performance disparity across languages. To address this, we introduce…

Computation and Language · Computer Science 2025-10-01 Fahim Faisal , Kaiqiang Song , Song Wang , Simin Ma , Shujian Liu , Haoyun Deng , Sathish Reddy Indurthi

Large language models (LLMs) are increasingly deployed as multi-step decision-making agents, where effective reward design is essential for guiding learning. Although recent work explores various forms of reward shaping and step-level…

Machine Learning · Computer Science 2026-02-26 Dengjia Zhang , Xiaoou Liu , Lu Cheng , Yaqing Wang , Kenton Murray , Hua Wei

This paper introduces RLNVR (Reinforcement Learning from Non-Verified Rewards), a framework for training language models using noisy, real-world feedback signals without requiring explicit human verification. Traditional RLHF requires…

Artificial Intelligence · Computer Science 2025-08-19 Rohit Krishnan , Jon Evans

Fine-tuning large language models (LLMs) for downstream tasks typically exhibit a fundamental safety-capability tradeoff, where improving task performance degrades safety alignment even on benign datasets. This degradation persists across…

Policy-based reinforcement learning currently plays an important role in improving LLMs on mathematical reasoning tasks. However, existing rollout-based reinforcement learning methods (GRPO, DAPO, GSPO, etc.) fail to explicitly consider…

Machine Learning · Computer Science 2025-09-25 Guochao Jiang , Wenfeng Feng , Guofeng Quan , Chuzhan Hao , Yuewei Zhang , Guohua Liu , Hao Wang

Extrinsic rewards can effectively guide reinforcement learning (RL) agents in specific tasks. However, extrinsic rewards frequently fall short in complex environments due to the significant human effort needed for their design and…

Machine Learning · Computer Science 2025-04-28 Mingqi Yuan , Roger Creus Castanyer , Bo Li , Xin Jin , Wenjun Zeng , Glen Berseth

Reinforcement Learning from Verifiable Rewards (RLVR) on chain-of-thought reasoning has become a standard part of language model post-training recipes. A common assumption is that the reasoning chains trained through RLVR reliably represent…

Computation and Language · Computer Science 2026-04-27 Qinan Yu , Alexa Tartaglini , Peter Hase , Carlos Guestrin , Christopher Potts

Reinforcement Learning with Verifiable Rewards (RLVR) has become a key paradigm to improve the reasoning capabilities of Multimodal Large Language Models (MLLMs). However, prevalent group-based algorithms such as GRPO require multi-rollout…

Machine Learning · Computer Science 2025-12-23 Rui Liu , Dian Yu , Lei Ke , Haolin Liu , Yujun Zhou , Zhenwen Liang , Haitao Mi , Pratap Tokekar , Dong Yu

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a dominant paradigm for enhancing Large Language Models (LLMs) reasoning, yet its reliance on external verifiers limits its scalability. Recent findings suggest that RLVR…

Machine Learning · Computer Science 2026-05-25 Xin-Qiang Cai , Masashi Sugiyama

We propose a generic reward shaping approach for improving the rate of convergence in reinforcement learning (RL), called Self Improvement Based REwards, or SIBRE. The approach is designed for use in conjunction with any existing RL…

Machine Learning · Computer Science 2020-12-22 Somjit Nath , Richa Verma , Abhik Ray , Harshad Khadilkar

Reinforcement learning (RL) has significantly improved the reasoning ability of large language models. However, current reward models underperform in challenging reasoning scenarios and predominant RL training paradigms rely on rule-based…

Computation and Language · Computer Science 2025-07-30 Meng Zhou , Bei Li , Jiahao Liu , Xiaowen Shi , Yang Bai , Rongxiang Weng , Jingang Wang , Xunliang Cai

The prevailing paradigm for training large reasoning models--combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR)--is fundamentally constrained by its reliance on high-quality, human-annotated…

Machine Learning · Computer Science 2026-03-24 Yuanfu Wang , Zhixuan Liu , Xiangtian Li , Chaochao Lu , Chao Yang

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…

Computation and Language · Computer Science 2026-05-29 Redacted by arXiv

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an important paradigm for unlocking reasoning capabilities in large language models, exemplified by the success of OpenAI o1 and DeepSeek-R1. Currently, Group Relative…

Machine Learning · Computer Science 2026-01-08 Shijie Zhang , Kevin Zhang , Zheyuan Gu , Xiang Guo , Rujun Guo , Shaoyu Liu , Guanjun Jiang , Xiaozhao Wang

Reinforcement Learning with Verifiable Rewards~(RLVR) has become a prominent paradigm to enhance the capabilities (i.e.\ long-context) of Large Language Models~(LLMs). However, it often relies on gold-standard answers or explicit evaluation…

Computation and Language · Computer Science 2026-03-03 Yao Xiao , Lei Wang , Yue Deng , Guanzheng Chen , Ziqi Jin , Jung-jae Kim , Xiaoli Li , Roy Ka-wei Lee , Lidong Bing

Reinforcement Learning with Verifiable Rewards (RLVR) serves as a cornerstone technique for enhancing the reasoning capabilities of Large Language Models (LLMs). However, its training is often plagued by \emph{entropy collapse}, a rapid…

Machine Learning · Computer Science 2026-04-30 Zhezheng Hao , Hong Wang , Haoyang Liu , Jian Luo , Jiarui Yu , Hande Dong , Qiang Lin , Can Wang , Jiawei Chen

Mathematical reasoning is a central challenge for large language models (LLMs), requiring not only correct answers but also faithful reasoning processes. Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising…

Machine Learning · Computer Science 2025-12-02 Md Tanvirul Alam , Nidhi Rastogi

Reinforcement learning has become a cornerstone for enhancing the reasoning capabilities of Large Language Models, where group-based approaches such as GRPO have emerged as efficient paradigms that optimize policies by leveraging…

Reinforcement learning with verifiable rewards (RLVR) has emerged as a prominent paradigm for enhancing the reasoning capabilities of large language models (LLMs). However, the entropy of LLMs usually collapses during RLVR training, leading…

Computation and Language · Computer Science 2026-04-21 Renren Jin , Pengzhi Gao , Yuqi Ren , Zhuowen Han , Tongxuan Zhang , Wuwei Huang , Wei Liu , Jian Luan , Deyi Xiong