English
Related papers

Related papers: RL2ML: Finite-Rollout Surrogate Objectives from Re…

200 papers

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

Reinforcement Learning with Verifiable Rewards (RLVR), which uses simple binary feedback to post-train large language models, has found significant empirical success. However, a principled understanding of why it works is lacking. This…

Machine Learning · Computer Science 2026-05-08 Joe Suk , Yaqi Duan

Large language models (LLMs) trained via KL-regularized reinforcement learning demonstrate strong instruction following, self-correction, and reasoning abilities. Yet their theoretical underpinnings remain limited. We exploit the…

Machine Learning · Computer Science 2025-12-23 Zhiquan Tan , Yinrong Hong

Action-conditioned robot world models generate future video frames of the manipulated scene given a robot action sequence, offering a promising alternative for simulating tasks that are difficult to model with traditional physics engines.…

Robotics · Computer Science 2026-03-27 Jai Bardhan , Patrik Drozdik , Josef Sivic , Vladimir Petrik

The application of rule-based reinforcement learning (RL) to multimodal large language models (MLLMs) introduces unique challenges and potential deviations from findings in text-only domains, particularly for perception-heavy tasks. This…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Zifu Wang , Junyi Zhu , Bo Tang , Zhiyu Li , Feiyu Xiong , Jiaqian Yu , Matthew B. Blaschko

We introduce Reinforcement Learning (RL) with Adaptive Verifiable Environments (RLVE), an approach using verifiable environments that procedurally generate problems and provide algorithmically verifiable rewards, to scale up RL for language…

Although Neural Machine Translation (NMT) models have advanced state-of-the-art performance in machine translation, they face problems like the inadequate translation. We attribute this to that the standard Maximum Likelihood Estimation…

Computation and Language · Computer Science 2018-11-22 Xiang Kong , Zhaopeng Tu , Shuming Shi , Eduard Hovy , Tong Zhang

The ongoing debate on whether reinforcement learning with verifiable rewards (RLVR) expands or shrinks the reasoning capabilities of large language models (LLMs) remains unresolved. Some studies contend that RLVR mainly improves sampling…

Machine Learning · Computer Science 2025-10-07 Xinhao Yao , Lu Yu , Xiaolin Hu , Fengwei Teng , Qing Cui , Jun Zhou , Yong Liu

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…

Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms are known to be sensitive to the task distribution…

Machine Learning · Computer Science 2021-03-02 Zichuan Lin , Garrett Thomas , Guangwen Yang , Tengyu Ma

We introduce Robust Multi-Objective Decoding (RMOD), a novel inference-time algorithm that robustly aligns Large Language Models (LLMs) to multiple human objectives (e.g., instruction-following, helpfulness, safety) by maximizing the…

Machine Learning · Computer Science 2026-02-17 Seongho Son , William Bankes , Sangwoong Yoon , Shyam Sundhar Ramesh , Xiaohang Tang , Ilija Bogunovic

Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in logical reasoning tasks, yet whether large language model (LLM) alignment requires fundamentally different approaches remains unclear. Given the…

Artificial Intelligence · Computer Science 2026-03-12 Zhaowei Zhang , Xiaohan Liu , Xuekai Zhu , Junchao Huang , Ceyao Zhang , Zhiyuan Feng , Yaodong Yang , Xiaoyuan Yi , Xing Xie

Retrieval-augmented generation enhances large language models (LLMs) by incorporating relevant information from external knowledge sources. This enables LLMs to adapt to specific domains and mitigate hallucinations in knowledge-intensive…

Computation and Language · Computer Science 2024-06-05 Lingxi Zhang , Yue Yu , Kuan Wang , Chao Zhang

Reinforcement learning (RL) has proven remarkably effective at improving the accuracy of language models in verifiable and deterministic domains like mathematics. Here, we examine if current RL methods are also effective at optimizing…

Machine Learning · Computer Science 2025-08-19 Michael Bereket , Jure Leskovec

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

Model-based Reinforcement Learning (MBRL) aims to make agents more sample-efficient, adaptive, and explainable by learning an explicit model of the environment. While the capabilities of MBRL agents have significantly improved in recent…

Machine Learning · Computer Science 2024-04-09 Ran Wei , Nathan Lambert , Anthony McDonald , Alfredo Garcia , Roberto Calandra

Reinforcement learning with verifiable rewards (RLVR) has demonstrated promising potential to enhance the reasoning capabilities of large language models (LLMs) in domains such as mathematics and coding. However, its applications on…

Computation and Language · Computer Science 2026-05-19 Zhonghang Yuan , Zhefan Wang , Fang Hu , Zihong Chen , Jinzhe Li , Gang Li , Jie Ying , Huanjun Kong , Songyang Zhang , Nanqing Dong

RL-based techniques can be employed to search for prompts that, when fed into a target language model, maximize a set of user-specified reward functions. However, in many target applications, the natural reward functions are in tension with…

Computation and Language · Computer Science 2025-06-10 Yasaman Jafari , Dheeraj Mekala , Rose Yu , Taylor Berg-Kirkpatrick

Deep Reinforcement Learning (RL) is remarkably effective in addressing sequential resource allocation problems in domains such as healthcare, public policy, and resource management. However, deep RL policies often lack transparency and…

Machine Learning · Computer Science 2025-02-18 Mauricio Tec , Guojun Xiong , Haichuan Wang , Francesca Dominici , Milind Tambe

Trustworthy verifiers are essential for the success of reinforcement learning with verifiable reward (RLVR), which is the core methodology behind various large reasoning models such as DeepSeek-R1. In complex domains like mathematical…

Machine Learning · Computer Science 2025-10-08 Yuzhen Huang , Weihao Zeng , Xingshan Zeng , Qi Zhu , Junxian He