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。
Jeffrey Amico, Gabriel Passamani Andrade, John Donaghy +12 authors
Swarm sAmpling Policy Optimization (SAPO) is a decentralized and asynchronous RL algorithm that enhances post-training language models without supervised fine-tuning, achieving significant reward gains and scalability across diverse hardware.
DeepReinforce Team, Xiaoya Li, Xiaofei Sun +4 authors
GrandCode is a multi-agent reinforcement learning system that outperforms human competitors in competitive programming challenges by orchestrating specialized agent modules and employing novel reward policy optimization techniques.
Kimi Team, Tongtong Bai, Yifan Bai +399 authors
Kimi K3 is a large-scale mixture-of-experts model with native vision and long-context capabilities that improves scaling efficiency and achieves strong performance across coding, reasoning, and agentic tasks.
Ke Yang, Chenglong Wang, Michel Galley +4 authors
StudentSim trains personalized student simulators from sparse data to mirror learner responses and adapt to tutor guidance, outperforming existing models across chess, writing, and math.
DeepSeek-AI, Daya Guo, Dejian Yang +197 authors
DeepSeek-R1-Zero and DeepSeek-R1 utilize reinforcement learning and multi-stage training to enhance reasoning capabilities, with DeepSeek-R1 achieving performance comparable to OpenAI-o1-1217.
Xiyuan Yang, Sheikh Sarwar, Jingru Cheng +8 authors
World Model RL replaces costly environment execution with a learned world model and applies debiasing and denoising to accelerate post-training of autonomous research agents.
Qwen, An Yang, Baosong Yang +39 authors
Qwen2.5, an enhanced series of large language models, demonstrates superior performance across various benchmarks and use cases through extensive pre-training and advanced post-training techniques.
Chiyu Ma, Shuo Yang, Kexin Huang +7 authors
FIPO enhances reinforcement learning for language models by using discounted future-KL divergence to improve credit assignment and extend reasoning chains, achieving better mathematical problem-solving performance.
Qihan Ren, Peng Wang, Ruikun Cai +8 authors
Supervised finetuning and reinforcement learning exhibit conditional cross-domain generalization in reasoning tasks, influenced by optimization dynamics, data quality, and model capability, with asymmetric outcomes between reasoning improvement and safety degradation.
Chujie Zheng, Shixuan Liu, Mingze Li +9 authors
Group Sequence Policy Optimization (GSPO) is a reinforcement learning algorithm that improves training efficiency and performance of large language models by using sequence-level importance ratios and operations.
Jian Yang, Xianglong Liu, Weifeng Lv +68 authors
A comprehensive guide to code LLMs, covering their lifecycle from data curation to deployment, including techniques, trade-offs, and research-practice gaps.
Shelly Bensal, Umar Jamil, Christopher Bryant +5 authors
A method using self-reflection and reinforcement learning improves the performance of large language models, especially with limited feedback, by rewarding self-reflections that lead to better task performance.
Kai Zhang, Xiangchao Chen, Bo Liu +27 authors
Early experience, using agent-generated interaction data without reward signals, improves policy effectiveness and generalization, serving as a bridge between imitation learning and reinforcement learning.
Chengsong Huang, Zifeng Wang, Rujun Han +14 authors
EnvHarness and EnvRigger dynamically reshape static environments via programmable plugins to target agent weaknesses and improve reinforcement learning co-evolution.
Haifeng Wang, Hua Wu, Tian Wu +435 authors
ERNIE 5.0 is a production-scale trillion-parameter autoregressive model that unifies multimodal understanding and generation through sparse MoE architecture and elastic training.
Guibin Zhang, Hejia Geng, Xiaohang Yu +22 authors
Agentic reinforcement learning transforms large language models into autonomous decision-making agents by leveraging temporally extended POMDPs, enhancing capabilities like planning and reasoning through reinforcement learning.
Vladimir Arkhipkin, Vladimir Korviakov, Nikolai Gerasimenko +22 authors
Kandinsky 5.0 is a family of state-of-the-art generative models for high-resolution images and short videos, featuring model lineups with varying parameters and enhanced training techniques to achieve superior quality and performance.
Shih-Yang Liu, Xin Dong, Ximing Lu +10 authors
Multi-reward reinforcement learning suffers from reward normalization collapse in GRPO, which GDPO addresses by decoupling reward normalization for improved training stability and performance across reasoning tasks.
Guobin Shen, Chenxiao Zhao, Xiang Cheng +2 authors
VESPO addresses training instability in LLM reinforcement learning by using variational formulation with variance reduction to correct policy divergence without length normalization.
GLM-4. 5 Team, Aohan Zeng, Xin Lv +168 authors
GLM-4.5, a Mixture-of-Experts large language model with 355B parameters, achieves strong performance across agentic, reasoning, and coding tasks using multi-stage training and reinforcement learning.
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