强化学习论文趋势 2023–2026

主要结论

• 强化学习论文从 2023 年的 1,070 篇增长到 2026 年的 2,985 篇，三年间扩大到约 2.8 倍。
• NeurIPS 是发强化学习论文最多的会议，2023–2026 年共 2,494 篇，占四个会议总量的 36%。
• 交叉方向里涨得最快的是推理模型：同时属于两个主题的论文从 2023 年的 9 篇增至 2026 年的 437 篇。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026\texttt{FEROM}: Frontier Endogenous Reveal-Order Marginal Policy Optimization for Masked Diffusion LMs
• ICML 2026$\text{DT}^\text{2}$: Decision-Targeted Digital Twins
• ICLR 2026$\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Textual Space
• CVPR 2026A Causal Marriage between VLM and IRM from Understanding to
• NeurIPS 2025$\texttt{G1}$: Teaching LLMs to Reason on Graphs with Reinforcement Learning
• ICML 2025A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs
• ICLR 2025$\phi$-Update: A Class of Policy Update Methods with Policy Convergence Guarantee
• CVPR 2025All-Optical Nonlinear Diffractive Deep Network for Ultrafast Image Denoising
• NeurIPS 2024A Critical Evaluation of AI Feedback for Aligning Large Language Models
• ICML 2024${\rm E}(3)$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
• ICLR 2024A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
• CVPR 2024DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning
• NeurIPS 2023“Why Not Looking backward?” A Robust Two-Step Method to Automatically Terminate Bayesian Optimization
• ICML 2023A Connection between One-Step RL and Critic Regularization in Reinforcement Learning
• ICLR 2023$O(T^{-1})$ Convergence of Optimistic-Follow-the-Regularized-Leader in Two-Player Zero-Sum Markov Games
• CVPR 2023"Seeing" Electric Network Frequency From Events
• NeurIPS 2026$\varphi$TD: Distributional Reinforcement Learning using Characteristic Functions
• ICML 2026$\textit{S}$-SPPO: Semantic-Calibrated Self-Play Preference Optimization
• ICLR 2026$AutoDrive\text{-}P^3$: Unified Chain of Perception–Prediction–Planning Thought via Reinforcement Fine-Tuning
• CVPR 2026AdaptVision Efficient Vision-Language Models via Adaptive Visual Acquisition

全部强化学习论文

共 1,640 篇，第 2 / 33 页

51. CVPR 2025SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories
52. CVPR 2025SeqMvRL: A Sequential Fusion Framework for Multi-view Representation Learning
53. CVPR 2025Seurat: From Moving Points to Depth
54. CVPR 2025SkillMimic: Learning Basketball Interaction Skills from Demonstrations
55. CVPR 2025SmartEraser: Remove Anything from Images using Masked-Region Guidance
56. CVPR 2025Spk2SRImgNet: Super-Resolve Dynamic Scene from Spike Stream via Motion Aligned Collaborative Filtering
57. CVPR 2025Stabilizing and Accelerating Autofocus with Expert Trajectory Regularized Deep Reinforcement Learning
58. CVPR 2025Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos
59. CVPR 2025Structure-from-Motion with a Non-Parametric Camera Model
60. CVPR 2025Three-view Focal Length Recovery From Homographies
61. CVPR 2025Touch2Shape: Touch-Conditioned 3D Diffusion for Shape Exploration and Reconstruction
62. CVPR 2025Toward Robust Neural Reconstruction from Sparse Point Sets
63. CVPR 2025Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards
64. CVPR 2025Tra-MoE: Learning Trajectory Prediction Model from Multiple Domains for Adaptive Policy Conditioning
65. CVPR 2025UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping
66. CVPR 2025Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior
67. CVPR 2025Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation
68. CVPR 2025VideoWorld: Exploring Knowledge Learning from Unlabeled Videos
69. CVPR 2025ViUniT: Visual Unit Tests for More Robust Visual Programming
70. CVPR 2025VLMs-Guided Representation Distillation for Efficient Vision-Based Reinforcement Learning
71. CVPR 2025VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction
72. CVPR 2025WildAvatar: Learning In-the-wild 3D Avatars from the Web
73. ICLR 2025$\phi$-Update: A Class of Policy Update Methods with Policy Convergence Guarantee
74. ICLR 2025$q$-exponential family for policy optimization
75. ICLR 20253DMolFormer: A Dual-channel Framework for Structure-based Drug Discovery
76. ICLR 2025A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety
77. ICLR 2025A Causal Lens for Learning Long-term Fair Policies
78. ICLR 2025A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement
79. ICLR 2025A Distributional Approach to Uncertainty-Aware Preference Alignment Using Offline Demonstrations
80. ICLR 2025A Generalist Hanabi Agent
81. ICLR 2025A Policy-Gradient Approach to Solving Imperfect-Information Games with Best-Iterate Convergence
82. ICLR 2025A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals
83. ICLR 2025A Theoretical Framework for Partially-Observed Reward States in RLHF
84. ICLR 2025Accelerating Goal-Conditioned Reinforcement Learning Algorithms and Research
85. ICLR 2025Accelerating Task Generalisation with Multi-Level Skill Hierarchies
86. ICLR 2025Accelerating Training with Neuron Interaction and Nowcasting Networks
87. ICLR 2025Action abstractions for amortized sampling
88. ICLR 2025Actions Speak Louder Than Words: Rate-Reward Trade-off in Markov Decision Processes
89. ICLR 2025ACTIVE: Offline Reinforcement Learning via Adaptive Imitation and In-sample $V$-Ensemble
90. ICLR 2025ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning
91. ICLR 2025Ada-K Routing: Boosting the Efficiency of MoE-based LLMs
92. ICLR 2025Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning
93. ICLR 2025Adaptive Gradient Clipping for Robust Federated Learning
94. ICLR 2025Adaptive teachers for amortized samplers
95. ICLR 2025AdaWM: Adaptive World Model based Planning for Autonomous Driving
96. ICLR 2025Adding Conditional Control to Diffusion Models with Reinforcement Learning
97. ICLR 2025Advantage Alignment Algorithms
98. ICLR 2025Adversarial Generative Flow Network for Solving Vehicle Routing Problems
99. ICLR 2025Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning
100. ICLR 2025AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation

常见问题

2023–2026 年四大会议一共有多少篇强化学习论文？

共 6,885 篇，按年份分别是 2023 年 1,070 篇、2024 年 1,190 篇、2025 年 1,640 篇、2026 年 2,985 篇。

NeurIPS 2026 有多少篇强化学习论文？

NeurIPS 2026 有 760 篇强化学习论文，上一届是 784 篇。

ICLR 2026 有多少篇强化学习论文？

ICLR 2026 有 911 篇强化学习论文，上一届是 379 篇。

ICML 2026 有多少篇强化学习论文？

ICML 2026 有 1,021 篇强化学习论文，上一届是 405 篇。

CVPR 2026 有多少篇强化学习论文？

CVPR 2026 有 293 篇强化学习论文，上一届是 72 篇。

哪个会议的强化学习论文最多？

NeurIPS，2023–2026 年共 2,494 篇。