English
Related papers

Related papers: Self-Rewarding Rubric-Based Reinforcement Learning…

200 papers

DeepSeek-R1 has shown that long chain-of-thought (CoT) reasoning can naturally emerge through a simple reinforcement learning (RL) framework with rule-based rewards, where the training may directly start from the base models-a paradigm…

Machine Learning · Computer Science 2025-08-07 Weihao Zeng , Yuzhen Huang , Qian Liu , Wei Liu , Keqing He , Zejun Ma , Junxian He

The rapid rise in AI conference submissions has driven increasing exploration of large language models (LLMs) for peer review support. However, LLM-based reviewers often generate superficial, formulaic comments lacking substantive,…

Computation and Language · Computer Science 2026-04-17 Zhuofeng Li , Yi Lu , Dongfu Jiang , Haoxiang Zhang , Yuyang Bai , Chuan Li , Yu Wang , Shuiwang Ji , Jianwen Xie , Yu Zhang

Reward modeling (RM), which captures human preferences to align large language models (LLMs), is increasingly employed in tasks such as model finetuning, response filtering, and ranking. However, due to the inherent complexity of human…

Computation and Language · Computer Science 2026-04-09 Pankayaraj Pathmanathan , Furong Huang

Reward design is central to reinforcement learning from human feedback (RLHF) and alignment research. In this work, we propose a unified framework to study hard, continuous, and hybrid reward structures for fine-tuning large language models…

Machine Learning · Computer Science 2025-11-18 Subramanyam Sahoo

We introduce Reasoning Gym (RG), a library of reasoning environments for reinforcement learning with verifiable rewards. It provides over 100 data generators and verifiers spanning multiple domains including algebra, arithmetic,…

Machine Learning · Computer Science 2025-10-21 Zafir Stojanovski , Oliver Stanley , Joe Sharratt , Richard Jones , Abdulhakeem Adefioye , Jean Kaddour , Andreas Köpf

Learning from feedback is an instrumental process for advancing the capabilities and safety of frontier models, yet its effectiveness is often constrained by cost and scalability. We present a pilot study that explores scaling reward models…

Machine Learning · Computer Science 2026-03-17 Jingxuan Fan , Yueying Li , Zhenting Qi , Dinghuai Zhang , Kianté Brantley , Sham M. Kakade , Hanlin Zhang

Reward Models, essential for guiding Large Language Model optimization, are typically trained on fixed preference datasets, resulting in rigid alignment to single, implicit preference distributions. This prevents adaptation to diverse…

Computation and Language · Computer Science 2025-07-08 Zhuohao Yu , Jiali Zeng , Weizheng Gu , Yidong Wang , Jindong Wang , Fandong Meng , Jie Zhou , Yue Zhang , Shikun Zhang , Wei Ye

Recent Reinforcement Learning (RL) advances for Large Language Models (LLMs) have improved reasoning tasks, yet their resource-constrained application to medical imaging remains underexplored. We introduce ChexReason, a vision-language…

Reinforcement Learning with Rubric Rewards (RLRR) is a framework that extends conventional reinforcement learning from human feedback (RLHF) and verifiable rewards (RLVR) by replacing scalar preference signals with structured,…

Machine Learning · Computer Science 2026-05-08 Guangchen Lan , Lian Xiong , Xin Zhou , Hejie Cui , Yuwei Zhang , Mao Li , Zhenyu Shi , Besnik Fetahu , Lihong Li , Xian Li

The central challenge of reinforcement learning for reasoning lies not only in the sparsity of outcome-level supervision, but more fundamentally in how to transform feedback provided only at the end of a sequence into fine-grained learning…

Machine Learning · Computer Science 2026-05-26 Fei Ding , Yongkang Zhang , Runhao Liu , Yuhao Liao , Zijian Zeng , Sibo wang , Huiming Yang

The widespread adoption of reinforcement learning-based alignment highlights the growing importance of reward models. Various benchmarks have been built to evaluate reward models in various domains and scenarios. However, a significant gap…

Computation and Language · Computer Science 2026-03-16 Hui Huang , Yancheng He , Wei Liu , Muyun Yang , Jiaheng Liu , Kehai Chen , Bing Xu , Conghui Zhu , Hailong Cao , Tiejun Zhao

Reinforcement learning with verifiable rewards can improve LLM reasoning, but learning remains sample-inefficient when terminal rewards are sparse. This has motivated a growing line of work on RL with textual feedback, where a critic model…

Machine Learning · Computer Science 2026-05-26 Utsav Singh , Sidhaarth Sredharan , Souradip Chakraborty , Amrit Singh Bedi

Generative Reward Models (GRMs) provide greater flexibility than scalar reward models in capturing human preferences, but their effectiveness is limited by poor reasoning capabilities. This often results in incomplete or overly speculative…

Computation and Language · Computer Science 2025-06-23 Bin Chen , Xinzge Gao , Chuanrui Hu , Penghang Yu , Hua Zhang , Bing-Kun Bao

Training large language models with reinforcement learning (RL) against verifiable rewards significantly enhances their reasoning abilities, yet remains computationally expensive due to inefficient uniform prompt sampling. We introduce…

Machine Learning · Computer Science 2026-03-06 Ruiqi Zhang , Daman Arora , Song Mei , Andrea Zanette

Nowadays, training and evaluating DeepResearch-generated reports remain challenging due to the lack of verifiable reward signals. Accordingly, rubric-based evaluation has become a common practice. However, existing approaches either rely on…

Computation and Language · Computer Science 2026-02-04 Changze Lv , Jie Zhou , Wentao Zhao , Jingwen Xu , Zisu Huang , Muzhao Tian , Shihan Dou , Tao Gui , Le Tian , Xiao Zhou , Xiaoqing Zheng , Xuanjing Huang , Jie Zhou

End-of-course assessments play important roles in the ongoing attempt to improve instruction in physics courses. Comparison of students' performance on assessments before and after instruction gives a measure of student learning. In…

Physics Education · Physics 2014-07-15 Leanne Doughty , Marcos D. Caballero

We study the process through which reasoning models trained with reinforcement learning on verifiable rewards (RLVR) can learn to solve new problems. We find that RLVR drives performance in two main ways: (1) by compressing pass@$k$ into…

Machine Learning · Computer Science 2025-06-23 Vaskar Nath , Elaine Lau , Anisha Gunjal , Manasi Sharma , Nikhil Baharte , Sean Hendryx

Recent reinforcement learning (RL) approaches have advanced radiology report generation (RRG), yet two core limitations persist: (1) report-level rewards offer limited evidence-grounded guidance for clinical faithfulness; and (2) current…

Machine Learning · Computer Science 2026-04-16 Qin Zhou , Guoyan Liang , Qianyi Yang , Jingyuan Chen , Sai Wu , Chang Yao , Zhe Wang

Large Reasoning Models (LRMs) have shown remarkable capabilities in solving complex problems through reinforcement learning (RL), particularly by generating long reasoning traces. However, these extended outputs often exhibit substantial…

Computation and Language · Computer Science 2025-05-22 Wei Liu , Ruochen Zhou , Yiyun Deng , Yuzhen Huang , Junteng Liu , Yuntian Deng , Yizhe Zhang , Junxian He

Model-based evaluation is at the heart of successful model development -- as a reward model for training, and as a replacement for human evaluation. To train such evaluators, the standard approach is to collect a large amount of human…