English
Related papers

Related papers: Execution-Grounded Credit Assignment for GRPO in C…

200 papers

While reinforcement learning has advanced the alignment of text-to-image (T2I) models, state-of-the-art policy gradient methods are still hampered by training instability and high variance, hindering convergence speed and compromising image…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Jeongjae Lee , Jong Chul Ye

RAG systems are increasingly deployed in high-stakes domains where users expect outputs to be consistent across semantically equivalent queries. However, existing systems often exhibit significant inconsistencies due to variability in both…

Computation and Language · Computer Science 2025-10-07 Faisal Hamman , Chenyang Zhu , Anoop Kumar , Xujun Peng , Sanghamitra Dutta , Daben Liu , Alfy Samuel

Reinforcement learning for program repair is hindered by sparse execution feedback and coarse sequence-level rewards that obscure which edits actually fix bugs. We present BoostAPR, a three-stage framework addressing these challenges: (1)…

Artificial Intelligence · Computer Science 2026-05-14 Yuanhao Li , Hongbo Wang , Xiaotang Shang , Xunzhu Tang , Yiming Cao , Xuhong Chen

Reinforcement learning for multi-step reasoning with large language models (LLMs) typically relies on sparse terminal rewards, which creates a poorly conditioned credit-assignment problem: the final feedback is propagated uniformly across…

Machine Learning · Computer Science 2026-05-26 Fei Ding , Yongkang Zhang , Youwei Wang , Zijian Zeng

Recent advances in reinforcement learning (RL) have achieved great successes by leveraging the multimodality and exploration capability of diffusion policies. Among these approaches, one representative branch focuses on the sampling-based…

Robotics · Computer Science 2026-05-29 Shutong Ding , Zejia Zhong , Zhongyi Wang , Ke Hu , Bikang Pan , Jingya Wang , Ye Shi

Process reward models (PRMs) allow for fine-grained credit assignment in reinforcement learning (RL), and seemingly contrast with outcome reward models (ORMs), which assign a single reward to an entire trajectory. However, we provide…

Machine Learning · Computer Science 2026-05-29 Michael Sullivan , Alexander Koller

Reinforcement learning for open-ended text generation is constrained by the lack of verifiable rewards, necessitating reliance on judge models that require either annotated data or powerful closed-source models. Inspired by recent work on…

Computation and Language · Computer Science 2026-04-14 Xinda Wang , Zhengxu Hou , Yangshijie Zhang , Bingren Yan , Jialin Liu , Chenzhuo Zhao , Zhibo Yang , Bin-Bin Yang , Feng Xiao

Group Relative Policy Optimization (GRPO) assigns a single scalar advantage to all tokens in a completion. For structured generations with explicit segments and objectives, this couples unrelated reward signals across segments, leading to…

Machine Learning · Computer Science 2026-02-12 Kirill Pavlenko , Alexander Golubev , Simon Karasik , Boris Yangel

Tuning parameter selection is of critical importance for kernel ridge regression. To this date, data driven tuning method for divide-and-conquer kernel ridge regression (d-KRR) has been lacking in the literature, which limits the…

Machine Learning · Statistics 2019-02-20 Ganggang Xu , Zuofeng Shang , Guang Cheng

Recent advancements in reinforcement learning, particularly through Group Relative Policy Optimization (GRPO), have significantly improved multimodal large language models for complex reasoning tasks. However, two critical limitations…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Jisheng Dang , Jingze Wu , Teng Wang , Xuanhui Lin , Nannan Zhu , Hongbo Chen , Wei-Shi Zheng , Meng Wang , Tat-Seng Chua

Reinforcement Learning (RL) has proven highly effective at enhancing the complex reasoning abilities of Large Language Models (LLMs), yet underlying mechanisms driving this success remain largely opaque. Our analysis reveals that puzzling…

Artificial Intelligence · Computer Science 2025-09-30 Haozhe Wang , Qixin Xu , Che Liu , Junhong Wu , Fangzhen Lin , Wenhu Chen

The Credit Assignment Problem (CAP) refers to the longstanding challenge of Reinforcement Learning (RL) agents to associate actions with their long-term consequences. Solving the CAP is a crucial step towards the successful deployment of RL…

Machine Learning · Computer Science 2024-07-08 Eduardo Pignatelli , Johan Ferret , Matthieu Geist , Thomas Mesnard , Hado van Hasselt , Olivier Pietquin , Laura Toni

Reference-free evaluation metrics for grammatical error correction (GEC) have achieved high correlation with human judgments. However, these metrics are not designed to evaluate adversarial systems that aim to obtain unjustifiably high…

Computation and Language · Computer Science 2025-10-01 Takumi Goto , Yusuke Sakai , Taro Watanabe

Large reasoning models (LRMs) have emerged as a powerful paradigm for solving complex real-world tasks. In practice, these models are predominantly trained via Reinforcement Learning with Verifiable Rewards (RLVR), yet most existing…

Artificial Intelligence · Computer Science 2026-02-27 Qiannian Zhao , Chen Yang , Jinhao Jing , Yunke Zhang , Xuhui Ren , Lu Yu , Shijie Zhang , Hongzhi Yin

Group Relative Policy Optimization (GRPO) has emerged as a promising approach for improving the reasoning capabilities of large language models. However, it struggles to effectively balance the tradeoff between exploration and exploitation…

Computation and Language · Computer Science 2026-05-13 Cheng Wang , Qin Liu , Wenxuan Zhou , Muhao Chen

Retrieval-augmented generation (RAG) grounds large language models (LLMs) in up-to-date external evidence, yet existing multi-hop RAG pipelines still issue redundant subqueries, explore too shallowly, or wander through overly long search…

Computation and Language · Computer Science 2025-05-26 Yuelyu Ji , Rui Meng , Zhuochun Li , Daqing He

Radiology report generation requires advanced medical image analysis, effective temporal reasoning, and accurate text generation. Although recent innovations, particularly multimodal large language models, have shown improved performance,…

Computation and Language · Computer Science 2025-11-11 Kai Zhang , Christopher Malon , Lichao Sun , Martin Renqiang Min

Recent advancements adopt online reinforcement learning (RL) from LLMs to text-to-image rectified flow diffusion models for reward alignment. The use of group-level rewards successfully aligns the model with the targeted reward. However, it…

Machine Learning · Computer Science 2026-01-06 Yiyang Wang , Xi Chen , Xiaogang Xu , Yu Liu , Hengshuang Zhao

Relative entropy coding (REC) algorithms encode a sample from a target distribution $Q$ using a proposal distribution $P$ using as few bits as possible. Unlike entropy coding, REC does not assume discrete distributions or require…

Information Theory · Computer Science 2023-09-28 Gergely Flamich , Stratis Markou , Jose Miguel Hernandez Lobato

When learning common skills like driving, beginners usually have domain experts standing by to ensure the safety of the learning process. We formulate such learning scheme under the Expert-in-the-loop Reinforcement Learning where a guardian…

Artificial Intelligence · Computer Science 2021-11-02 Zhenghao Peng , Quanyi Li , Chunxiao Liu , Bolei Zhou