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。
Yuchen Fan, Kaiyan Zhang, Heng Zhou +15 authors
LLMs can serve as efficient simulators for RL tasks by leveraging internal knowledge, reducing reliance on external search engines and improving sim-to-real transfer.
Kaichen Zhang, Keming Wu, Zuhao Yang +5 authors
OpenMMReasoner, a two-stage training approach combining supervised fine-tuning and reinforcement learning, enhances multimodal reasoning performance through rigorous data curation and improved training strategies.
Zhihong Shao, Yuxiang Luo, Chengda Lu +6 authors
A self-verifying large language model for theorem proving improves mathematical reasoning by incentivizing rigorous step-by-step derivations and achieves high scores in international competitions.
Zheyuan Yang, Lyuhao Chen, Arman Cohan +1 authors
Two post-training strategies, distillation and RLVR, enable inference-time scaling in table reasoning tasks, resulting in a model (Table-R1-Zero) that matches GPT-4.1's performance using fewer parameters and shows strong generalization.
Zhen Li, Zian Meng, Shuwei Shi +5 authors
WildWorld is a large-scale dataset for action-conditioned world modeling that provides explicit state annotations from a photorealistic game, enabling better understanding of latent-state dynamics and long-horizon consistency.
Yuxiang Ji, Ziyu Ma, Yong Wang +3 authors
Tree-based Group Relative Policy Optimization (Tree-GRPO) enhances reinforcement learning for large language models by using tree search to improve rollouts and estimate grouped relative advantages, outperforming chain-based methods.
Zhiyuan Hu, Yunhai Hu, Juncheng Liu +9 authors
Multi-Agent Test-Time Reinforcement Learning (MATTRL) enhances multi-agent reasoning through structured textual experience injection and consensus-based decision making at inference time.
Ibragim Badertdinov, Maksim Nekrashevich, Anton Shevtsov +1 authors
A large-scale dataset of software engineering tasks spanning multiple programming languages and repositories was created using an automated pipeline that generates executable environments and filters unreliable instances through LLM validation.
Yibin Wang, Zhimin Li, Yuhang Zang +6 authors
Pref-GRPO, a pairwise preference reward-based GRPO method, enhances text-to-image generation by mitigating reward hacking and improving stability, while UniGenBench provides a comprehensive benchmark for evaluating T2I models.
Mingqi Wu, Zhihao Zhang, Qiaole Dong +9 authors
Research on enhancing reasoning capabilities in large language models using reinforcement learning reveals that accurate reward signals are crucial for performance improvement, and current benchmarks may be unreliable due to data contamination.
Fanqi Wan, Weizhou Shen, Shengyi Liao +7 authors
A framework called QwenLong-L1 enhances large reasoning models for long-context reasoning through reinforcement learning, achieving leading performance on document question-answering benchmarks.
Alexander Nikulin, Ilya Zisman, Alexey Zemtsov +3 authors
XLand-100B is a large-scale dataset for in-context reinforcement learning, containing extensive learning histories in the XLand-MiniGrid environment.
Jianhao Yan, Yafu Li, Zican Hu +5 authors
LUFFY enhances zero-RL models with off-policy guidance, improving reasoning and generalization through balanced imitation and exploration.
Daixuan Cheng, Shaohan Huang, Yuxian Gu +6 authors
LLM-in-Sandbox enables large language models to perform general intelligence tasks across diverse domains by allowing them to explore a code sandbox environment, achieving robust generalization without additional training.
Jingcheng Hu, Yinmin Zhang, Shijie Shang +17 authors
Parallel Coordinated Reasoning enables large-scale test-time compute scaling beyond sequential reasoning limitations through parallel exploration and message-passing architecture.
Xiaomi LLM-Core Team, Bingquan Xia, Bowen Shen +61 authors
MiMo-7B, a large language model optimized for reasoning tasks, enhances pre-training with data mixing and Multi-Token Prediction, and post-training with reinforcement learning on math and programming problems, achieving superior performance over larger models.
Runhui Huang, Qihui Zhang, Zhe Liu +3 authors
SpectraReward leverages pretrained multimodal language models as training-free reward models for image-generation reinforcement learning by measuring prompt recovery likelihood, with a self-improving variant that uses the policy's own understanding branch to close the loop.
Zongxia Li, Wenhao Yu, Chengsong Huang +8 authors
Vision-SR1 uses reinforcement learning to enhance visual reasoning in vision-language models by decomposing the process into visual perception and language reasoning stages, improving accuracy and reducing hallucinations.
Xiyao Wang, Chunyuan Li, Jianwei Yang +4 authors
Reinforcement learning on preference-labeled critic datasets enhances a generative model's performance, creating a unified multimodal system that excels in both evaluation and generation.
Zichen Wen, Boxue Yang, Shuang Chen +31 authors
Innovator-VL demonstrates that principled training design and transparent methodology can achieve strong scientific intelligence with reduced data requirements while maintaining general vision performance.
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