English
Related papers

Related papers: Exploring Pass-Rate Reward in Reinforcement Learni…

200 papers

Open-ended generation tasks require outputs to satisfy diverse and often implicit task-specific evaluation rubrics. The sheer number of relevant rubrics leads to prohibitively high verification costs and incomplete assessments of a…

Machine Learning · Computer Science 2025-11-04 Mian Wu , Gavin Zhang , Sewon Min , Sergey Levine , Aviral Kumar

Recent advancements in improving the reasoning capabilities of Large Language Models have underscored the efficacy of Process Reward Models (PRMs) in addressing intermediate errors through structured feedback mechanisms. This study analyzes…

Computation and Language · Computer Science 2025-06-03 Zhengyu Chen , Yudong Wang , Teng Xiao , Ruochen Zhou , Xuesheng Yang , Wei Wang , Zhifang Sui , Jingang Wang

Reinforcement learning (RL), particularly GRPO, improves image generation quality significantly by comparing the relative performance of images generated within the same group. However, in the later stages of training, the model tends to…

Computer Vision and Pattern Recognition · Computer Science 2025-12-29 Henglin Liu , Huijuan Huang , Jing Wang , Chang Liu , Xiu Li , Xiangyang Ji

Large language models~(LLMs) are expected to be helpful, harmless, and honest. In different alignment scenarios, such as safety, confidence, and general preference alignment, binary preference data collection and reward modeling are…

Computation and Language · Computer Science 2025-10-14 Shuai Zhao , Yunqiu Xu , Linchao Zhu , Yi Yang

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key method for improving Large Language Models' reasoning capabilities, yet recent evidence suggests it may paradoxically shrink the reasoning boundary rather than…

Artificial Intelligence · Computer Science 2025-10-03 Phuc Minh Nguyen , Chinh D. La , Duy M. H. Nguyen , Nitesh V. Chawla , Binh T. Nguyen , Khoa D. Doan

Reward design remains a significant bottleneck in applying reinforcement learning (RL) to real-world problems. A popular alternative is reward learning, where reward functions are inferred from human feedback rather than manually specified.…

Machine Learning · Computer Science 2026-01-16 Chaitanya Kharyal , Calarina Muslimani , Matthew E. Taylor

Process reward models (PRMs) provide more nuanced supervision compared to outcome reward models (ORMs) for optimizing policy models, positioning them as a promising approach to enhancing the capabilities of LLMs in complex reasoning tasks.…

Computation and Language · Computer Science 2025-05-30 Hongzhan Chen , Tao Yang , Shiping Gao , Ruijun Chen , Xiaojun Quan , Hongtao Tian , Ting Yao

Extending large language models (LLMs) to low-resource languages often incurs an "alignment tax": improvements in the target language come at the cost of catastrophic forgetting in general capabilities. We argue that this trade-off arises…

Computation and Language · Computer Science 2026-05-15 Zeli Su , Ziyin Zhang , Zhou Liu , Xuexian Song , Zhankai Xu , Longfei Zheng , Xiaolu Zhang , Rong Fu , Guixian Xu , Wentao Zhang

Group Relative Policy Optimization (GRPO) is widely used for reinforcement learning with verifiable rewards, but it often suffers from advantage collapse: when all rollouts in a group receive the same reward, the group yields zero relative…

Machine Learning · Computer Science 2026-04-02 Yu Xia , Canwen Xu , Zhewei Yao , Julian McAuley , Yuxiong He

Reinforcement learning with verifiable rewards has driven recent advances in LLM post-training, in particular for reasoning. Policy optimization algorithms generate a number of responses for a given prompt and then effectively weight the…

Machine Learning · Computer Science 2026-02-12 Reinhard Heckel , Mahdi Soltanolkotabi , Christos Thramboulidis

Reinforcement Learning (RL) can directly enhance the reasoning capabilities of large language models without extensive reliance on Supervised Fine-Tuning (SFT). In this work, we revisit the traditional Policy Gradient (PG) mechanism and…

Machine Learning · Computer Science 2026-02-04 Xiangxiang Chu , Hailang Huang , Xiao Zhang , Fei Wei , Yong Wang

Prevalent reinforcement learning~(RL) methods for fine-tuning LLM reasoners, such as GRPO or Leave-one-out PPO, abandon the learned value function in favor of empirically estimated returns. This hinders test-time compute scaling that relies…

Machine Learning · Computer Science 2026-04-14 Kusha Sareen , Morgane M Moss , Alessandro Sordoni , Rishabh Agarwal , Arian Hosseini

We tackle the problem of aligning pre-trained large language models (LMs) with human preferences. If we view text generation as a sequential decision-making problem, reinforcement learning (RL) appears to be a natural conceptual framework.…

Using learned reward functions (LRFs) as a means to solve sparse-reward reinforcement learning (RL) tasks has yielded some steady progress in task-complexity through the years. In this work, we question whether today's LRFs are best-suited…

Machine Learning · Computer Science 2023-08-24 Ademi Adeniji , Amber Xie , Carmelo Sferrazza , Younggyo Seo , Stephen James , Pieter Abbeel

Reinforcement learning (RL) is a key post-pretraining step for aligning large language models (LLMs) with complex tasks and human preferences. While it is often assumed that RL fine-tuning requires updating most of a model's parameters, we…

Machine Learning · Computer Science 2025-07-30 Andrii Balashov

Bugs in popular distributed protocol implementations have been the source of many downtimes in popular internet services. We describe a randomized testing approach for distributed protocol implementations based on reinforcement learning.…

Software Engineering · Computer Science 2024-09-05 Andrea Borgarelli , Constantin Enea , Rupak Majumdar , Srinidhi Nagendra

Recent advances in large language models (LLMs) have demonstrated that reinforcement learning with verifiable rewards (RLVR) can significantly enhance reasoning abilities by directly optimizing correctness, rather than relying solely on…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Minbin Huang , Runhui Huang , Chuanyang Zheng , Jingyao Li , Guoxuan Chen , Han Shi , Hong Cheng

Reinforcement learning (RL) has shown its strength in challenging sequential decision-making problems. The reward function in RL is crucial to the learning performance, as it serves as a measure of the task completion degree. In real-world…

Machine Learning · Computer Science 2024-02-13 Siyuan Li , Shijie Han , Yingnan Zhao , By Liang , Peng Liu

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

Code-generating Large Language Models (LLMs) have become essential tools in modern software development, enhancing productivity and accelerating development. This paper aims to investigate the fine-tuning of code-generating LLMs using…

Software Engineering · Computer Science 2025-05-06 Marina Sakharova , Abhinav Anand , Mira Mezini