English
Related papers

Related papers: Open-Reasoner-Zero: An Open Source Approach to Sca…

200 papers

Zero-shot reinforcement learning (RL) has emerged as a setting for developing general agents, capable of solving downstream tasks without additional training or planning at test-time. While conventional RL optimizes policies for fixed…

Machine Learning · Computer Science 2026-03-10 Jacopo Di Ventura , Jan Felix Kleuker , Aske Plaat , Thomas Moerland

OpenAI's recent introduction of Reinforcement Fine-Tuning (RFT) showcases the potential of reasoning foundation model and offers a new paradigm for fine-tuning beyond simple pattern imitation. This technical report presents \emph{OpenRFT},…

Artificial Intelligence · Computer Science 2024-12-24 Yuxiang Zhang , Yuqi Yang , Jiangming Shu , Yuhang Wang , Jinlin Xiao , Jitao Sang

Large language models can generate solutions to complex problems, but training them with reinforcement learning typically requires verifiable rewards that are expensive to create and not possible for all domains. We demonstrate that LLMs…

Machine Learning · Computer Science 2025-08-08 Toby Simonds , Kevin Lopez , Akira Yoshiyama , Dominique Garmier

The recent development of zero-shot reinforcement learning (RL) has opened a new avenue for learning pre-trained generalist policies that can adapt to arbitrary new tasks in a zero-shot manner. While the popular Forward-Backward…

Machine Learning · Computer Science 2025-10-24 Kexin Zheng , Lauriane Teyssier , Yinan Zheng , Yu Luo , Xianyuan Zhan

Most reinforcement learning (RL) methods for training large language models (LLMs) require ground-truth labels or task-specific verifiers, limiting scalability when correctness is ambiguous or expensive to obtain. We introduce Reinforcement…

Neural and Evolutionary Computing · Computer Science 2026-01-30 Micah Rentschler , Jesse Roberts

Recent works on large language models (LLMs) have successfully demonstrated the emergence of reasoning capabilities via reinforcement learning (RL). Although recent efforts leverage group relative policy optimization (GRPO) for MLLMs…

Computation and Language · Computer Science 2025-06-18 Shilin Xu , Yanwei Li , Rui Yang , Tao Zhang , Yueyi Sun , Wei Chow , Linfeng Li , Hang Song , Qi Xu , Yunhai Tong , Xiangtai Li , Hao Fei

Inspired by the success of DeepSeek-R1, we explore the potential of rule-based reinforcement learning (RL) in MLLM post-training for perception policy learning. While promising, our initial experiments reveal that incorporating a thinking…

Computer Vision and Pattern Recognition · Computer Science 2025-04-11 En Yu , Kangheng Lin , Liang Zhao , Jisheng Yin , Yana Wei , Yuang Peng , Haoran Wei , Jianjian Sun , Chunrui Han , Zheng Ge , Xiangyu Zhang , Daxin Jiang , Jingyu Wang , Wenbing Tao

Frontier reasoning models have exhibited incredible capabilities across a wide array of disciplines, driven by posttraining large language models (LLMs) with reinforcement learning (RL). However, despite the widespread success of this…

Machine Learning · Computer Science 2025-10-17 Aayush Karan , Yilun Du

Reasoning models represented by the Deepseek-R1-Distill series have been widely adopted by the open-source community due to their strong performance in mathematics, science, programming, and other domains. However, our study reveals that…

Artificial Intelligence · Computer Science 2025-06-16 Lin Sun , Weihong Lin , Jinzhu Wu , Yongfu Zhu , Xiaoqi Jian , Guangxiang Zhao , Change Jia , Linglin Zhang , Sai-er Hu , Yuhan Wu , Xiangzheng Zhang

Recent models such as OpenAI o1 and DeepSeek-R1 have demonstrated strong performance on reasoning-intensive tasks by generating extended Chain-of-Thought (CoT) traces. While longer reasoning helps with thorough exploration of solution paths…

Artificial Intelligence · Computer Science 2025-12-03 Jingyang Yi , Jiazheng Wang , Sida Li

Open reasoning language models are often compared under mixed sample sizes, partially standardized prompts, and accuracy-centered summaries, which makes practical model selection difficult to interpret. We present a unified evaluation of…

Computation and Language · Computer Science 2026-05-20 Md Motaleb Hossen Manik , Ge Wang

Recent advancements in reasoning-based Large Language Models (LLMs), particularly their potential through test-time scaling, have created significant opportunities for distillation in code generation and critique. However, progress in both…

We introduce SIRI, Scaling Iterative Reinforcement Learning with Interleaved Compression, a simple yet effective RL approach for Large Reasoning Models (LRMs) that enables more efficient and accurate reasoning. Existing studies have…

Machine Learning · Computer Science 2025-09-30 Haoming Wen , Yushi Bai , Juanzi Li , Jie Tang

Reinforcement learning (RL) has drawn increasing interests in recent years due to its tremendous success in various applications. However, standard RL algorithms can only be applied for single reward function, and cannot adapt to an unseen…

Machine Learning · Computer Science 2022-01-04 Ziyang Tang , Yihao Feng , Qiang Liu

We introduce MediX-R1, an open-ended Reinforcement Learning (RL) framework for medical multimodal large language models (MLLMs) that enables clinically grounded, free-form answers beyond multiple-choice formats. MediX-R1 fine-tunes a…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Sahal Shaji Mullappilly , Mohammed Irfan Kurpath , Omair Mohamed , Mohamed Zidan , Fahad Khan , Salman Khan , Rao Anwer , Hisham Cholakkal

Reinforcement Learning with Verifiable Rewards (RLVR) has recently demonstrated notable success in enhancing the reasoning performance of large language models (LLMs), particularly on mathematics and programming tasks. Similar to how…

Artificial Intelligence · Computer Science 2025-11-25 Yang Yue , Zhiqi Chen , Rui Lu , Andrew Zhao , Zhaokai Wang , Yang Yue , Shiji Song , Gao Huang

Training reasoning language models (LMs) with reinforcement learning (RL) for one-hot correctness inherently relies on the LM being able to explore and solve its task with some chance at initialization. Furthermore, a key use case of…

Machine Learning · Computer Science 2025-10-30 Edoardo Cetin , Tianyu Zhao , Yujin Tang

We introduce a novel training methodology named zELO, which optimizes retrieval performance via the analysis that ranking tasks are statically equivalent to a Thurstone model. Based on the zELO method, we use unsupervised data in order…

Artificial Intelligence · Computer Science 2025-09-17 Nicholas Pipitone , Ghita Houir Alami , Advaith Avadhanam , Anton Kaminskyi , Ashley Khoo

Large language models excel at short-horizon reasoning tasks, but performance drops as reasoning horizon lengths increase. Existing approaches to combat this rely on inference-time scaffolding or costly step-level supervision, neither of…

Self-play has enabled large language models to autonomously improve through self-generated challenges. However, existing self-play methods for vision-language models rely on passive interaction with static image collections, resulting in…

Computer Vision and Pattern Recognition · Computer Science 2026-02-13 Jinghan He , Junfeng Fang , Feng Xiong , Zijun Yao , Fei Shen , Haiyun Guo , Jinqiao Wang , Tat-Seng Chua