Trends · 研究趋势
数据来自 Hugging Face 论文的 AI 提取关键词,按月统计研究方向的增长与热度。
Andrew Zhao, Yiran Wu, Yang Yue +8 authors
Absolute Zero Reasoner (AZR) achieves state-of-the-art performance on coding and mathematical reasoning tasks through self-generated, verified learning without external data.
Shenzhi Wang, Le Yu, Chang Gao +15 authors
Token entropy patterns are crucial in RLVR, with high-entropy tokens significantly impacting reasoning performance and model optimization.
Chenxu Yang, Chuanyu Qin, Qingyi Si +7 authors
RLSD combines reinforcement learning with verifiable rewards and self-distillation to achieve stable training with fine-grained updates and reliable policy direction from environmental feedback.
Qinsi Wang, Bo Liu, Tianyi Zhou +6 authors
Vision-Zero is a domain-agnostic framework that enhances vision-language models through self-improvement in competitive visual games, using Iterative Self-Play Policy Optimization and achieving state-of-the-art performance without human annotation.
Yang Yue, Zhiqi Chen, Rui Lu +5 authors
Despite initial claims, reinforcement learning with verifiable rewards does not introduce fundamentally new reasoning abilities to LLMs, instead it enhances performance by biasing output distribution toward rewarded paths without expanding the reasoning boundary.
Junkang Wu, Kexin Huang, Jiancan Wu +3 authors
Quantile Advantage Estimation stabilizes reinforcement learning with verifiable rewards by addressing entropy issues and improving performance on large language models.
Yanqi Dai, Yuxiang Ji, Xiao Zhang +3 authors
MathForge enhances mathematical reasoning in large models through a dual framework combining difficulty-aware policy optimization and multi-aspect question reformulation to address limitations in existing reinforcement learning methods.
Ximing Lu, David Acuna, Jaehun Jung +12 authors
Golden Goose synthesizes unlimited RLVR tasks from unverifiable internet text by creating multiple-choice question-answering versions of fill-in-the-middle tasks, enabling large-scale training and achieving state-of-the-art results in cybersecurity and other domains.
Qinsi Wang, Jing Shi, Huazheng Wang +8 authors
RLSVR extends reinforcement learning with verifiable rewards to open-ended tasks by transforming them into self-verifiable proxy environments, demonstrated via a multi-agent spy game that yields automatic rewards for text generation and reasoning.
Xin Xu, Clive Bai, Kai Yang +7 authors
Composition-RL improves reasoning capabilities by automatically composing multiple problems into new verifiable questions for reinforcement learning training.
Shuaijie She, Yu Bao, Yu Lu +7 authors
DuPO is a dual learning framework that generates annotation-free feedback using a generalized duality, enhancing performance across various tasks without relying on costly labels.
Fang Wu, Weihao Xuan, Ximing Lu +2 authors
Reinforcement Learning with Verifiable Rewards (RLVR) enhances precision but may limit exploration and discovery of new solutions, suggesting potential limits to its effectiveness in expanding reasoning capabilities.
Dongfu Jiang, Yi Lu, Zhuofeng Li +9 authors
VerlTool is a unified and modular framework for Agentic Reinforcement Learning with Tool use, addressing inefficiencies in existing approaches and providing competitive performance across multiple domains.
Xiusi Chen, Gaotang Li, Ziqi Wang +9 authors
Reasoning Reward Models (ReasRMs) enhance reward modeling for large language models by integrating reasoning tasks, improving interpretability and performance.
Jian Hu, Xibin Wu, Weixun Wang +3 authors
OpenRLHF is an open-source RLHF framework that enhances training efficiency and accessibility for researchers and practitioners.
Zhiqin Yang, Jingwen Fu, Yuhan Liu +16 authors
This work proposes a structured ladder for scaling large reasoning models beyond human supervision by tracing autonomous rewards and self-generated experience, while identifying risks and evaluation dimensions.
Peixuan Han, Runhui Wang, Ketan Ramaneti +3 authors
Cliff improves reinforcement learning with verifiable rewards by using an off-the-shelf language model to detect the first reasoning error and shaping token-level advantages accordingly.
北京市昌平区探索星信息技术及软件开发工作室
京ICP备2026059466号