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。
Zhenghai Xue, Longtao Zheng, Qian Liu +4 authors
SimpleTIR stabilizes multi-turn Tool-Integrated Reasoning training by filtering out void turns, achieving state-of-the-art performance on math reasoning benchmarks.
Dian Zheng, Harry Lee, Manyuan Zhang +4 authors
InterleaveThinker enables interleaved generation capabilities for image generators through a multi-agent pipeline with planner and critic agents, achieving performance comparable to state-of-the-art models while enhancing reasoning benchmarks.
Junteng Liu, Yunji Li, Chi Zhang +12 authors
WebExplorer, a data-driven approach for developing advanced web agents, achieves state-of-the-art performance in information-seeking tasks through systematic data generation and reinforcement learning.
Zhaorun Chen, Zhuokai Zhao, Kai Zhang +15 authors
DreamGym is a unified framework that synthesizes diverse experiences for scalable online RL training, improving agent performance and reducing real-world interactions.
Dianyi Wang, Ruihang Li, Feng Han +17 authors
DeepGen 1.0 is a lightweight 5B unified multimodal model that achieves superior performance in image generation and editing through advanced alignment techniques and progressive training strategies.
Jiaqi Tang, Jianmin Chen, Youyang Zhai +6 authors
Robust-U1 enhances multimodal large language models' robustness against visual corruptions through self-recovery capabilities that improve both visual quality and reasoning performance.
Wei Xiong, Hanning Zhang, Chenlu Ye +3 authors
Self-rewarding reasoning large language models independently generate and correct their outputs during inference using a two-stage algorithmic framework, enhancing performance without external feedback.
Haozhan Li, Yuxin Zuo, Jiale Yu +18 authors
SimpleVLA-RL, an RL framework for VLA models, enhances long-horizon action planning, achieves state-of-the-art performance, and discovers novel patterns during training.
Guoxin Chen, Zile Qiao, Xuanzhong Chen +13 authors
IterResearch, an iterative deep-research paradigm, improves long-horizon reasoning by reformulating it as a Markov Decision Process with strategic workspace reconstruction and Efficiency-Aware Policy Optimization, achieving better performance and interaction scaling compared to existing agents.
Senqiao Yang, Junyi Li, Xin Lai +3 authors
VisionThink dynamically adjusts image resolution and visual token processing for efficient and effective vision-language tasks, improving performance and reducing computational cost.
Yizhi Li, Qingshui Gu, Zhoufutu Wen +14 authors
TreePO, a self-guided rollout algorithm for sequence generation, reduces computational cost and enhances exploration diversity in reinforcement learning for large language models.
Maggie Huan, Yuetai Li, Tuney Zheng +6 authors
Reinforcement learning-tuned models generalize better across domains compared to supervised fine-tuned models in reasoning tasks, indicating a need to reconsider standard training methods.
Xingtai Lv, Yuxin Zuo, Youbang Sun +9 authors
A unified policy gradient estimator and Hybrid Post-Training algorithm effectively combine online and offline data for post-training language models, improving performance across various benchmarks.
Peng Xia, Jianwen Chen, Hanyang Wang +10 authors
SkillRL enables LLM agents to improve through hierarchical skill discovery and recursive policy evolution, achieving superior performance on complex tasks while reducing computational overhead.
Taiwei Shi, Sihao Chen, Bowen Jiang +3 authors
Experiential Reinforcement Learning introduces an explicit experience-reflection-consolidation loop that improves learning efficiency and performance in sparse-reward environments by enabling structured behavioral revision without additional inference costs.
Yuxiang Wei, Olivier Duchenne, Jade Copet +6 authors
SWE-RL leverages reinforcement learning to enhance large language models' software engineering reasoning, achieving state-of-the-art performance and generalized reasoning skills by learning from extensive open-source software evolution data.
Daniil Plyusov, Alexey Gorbatovski, Boris Shaposhnikov +3 authors
RLVR methods using group sampling suffer from bias toward likely trajectories and missed rare-correct ones; a difficulty-aware advantage scaling technique improves performance on benchmarks without increasing computational cost.
Zhennan Shen, Yanshu Li, Qingyu Yin +6 authors
On-policy distillation exhibits distinct parameter space dynamics characterized by relaxed off-principal updates and subspace locking, forming a unique geometric pattern separate from supervised fine-tuning and reinforcement learning with verifiable rewards.
Zanlin Ni, Shenzhi Wang, Yang Yue +8 authors
Arbitrary order generation in diffusion large language models limits reasoning capability by causing premature solution space collapse, making standard policy optimization more effective.
Zafir Stojanovski, Oliver Stanley, Joe Sharratt +4 authors
Reasoning Gym provides a library of reasoning environments with verifiable rewards and procedural data generation for reinforcement learning, enabling the evaluation and training of reasoning models at varying difficulty levels.
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