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 6,885 篇，第 4 / 138 页

151. CVPR 2026Monet Reasoning in Latent Visual Space Beyond Image and Language
152. CVPR 2026MorphSeek Fine-grained Latent Representation-Level Policy Optimization for Deformable Image Registration
153. CVPR 2026MSJoE Jointly Evolving MLLM and Sampler for Efficient Long-Form Video
154. CVPR 2026MSRL Scaling Generative Multimodal Reward Modeling via Multi-Stage Reinforcement Learning
155. CVPR 2026MultiCrafter High-Fidelity Multi-Subject Generation via Disentangled Attention and Identity-Aware Preference
156. CVPR 2026Neuro-Cognitive Reward Modeling for Human-Centered Autonomous Vehicle Control
157. CVPR 2026NIL No-data Imitation Learning
158. CVPR 2026NoRD A Data-Efficient Vision-Language-Action Model that Drives without Reasoning
159. CVPR 2026NS-Diff Fluid Navier-Stokes Guided Video Diffusion via Reinforcement Learning
160. CVPR 2026OddGridBench Exposing the Lack of Fine-Grained Visual Discrepancy Sensitivity in
161. CVPR 2026Omni-Fake Benchmarking Unified Multimodal Social Media Deepfake Detection
162. CVPR 2026OmniVTG A Large-Scale Dataset and Training Paradigm for Open-World Video
163. CVPR 2026OneThinker All-in-one Reasoning Model for Image and Video
164. CVPR 2026OpenMMReasoner Pushing the Frontiers in Multimodal Reasoning with an Open
165. CVPR 2026OralGPT-Plus Learning to Use Visual Tools via Reinforcement Learning for
166. CVPR 2026OraPO Oracle-educated Reinforcement Learning for Data-efficient and Factual Radiology Report
167. CVPR 2026PaCo-RL Advancing Reinforcement Learning for Consistent Image Generation with Pairwise
168. CVPR 2026PanoEnv Exploring 3D Spatial Intelligence in Panoramic Environments with Reinforcement
169. CVPR 2026Parameter-efficient Continual Learning for Enhancing Plasticity without Forgetting under Limited
170. CVPR 2026ParaUni Enhance Generation in Unified Multimodal Model with Reinforcement-driven Hierarchical
171. CVPR 2026PDCR Perception-Decomposed Confidence Reward for Vision-Language Reasoning
172. CVPR 2026Perceptual-Evidence Anchored Reinforced Learning for Multimodal Reasoning
173. CVPR 2026POCA Pareto-Optimal Curriculum Alignment for Visual Text Generation
174. CVPR 2026PointThinker Point-Incentivized Parallel Thinking for Multimodal Large Language Model
175. CVPR 2026Predicting Spatial Transcriptomics from Histology Images via High-Order Multi-Cell Interaction
176. CVPR 2026PromptEnhancer Taming Your Rewriter for Text-to-Image Generation via Fine-Grained Reward
177. CVPR 2026PromptLoop Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model
178. CVPR 2026PROMPTMINER Black-Box Prompt Stealing against Text-to-Image Generative Models via Reinforcement
179. CVPR 2026PSR Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards
180. CVPR 2026Push-and-Step From RL-Based Balance Recovery to Physical Simulation of Dense
181. CVPR 2026PvP Data-Efficient Humanoid Robot Learning with Proprioceptive-Privileged Contrastive Representations
182. CVPR 2026R-4B Incentivizing General-Purpose Auto-Thinking in MLLMs via Bi-Mode Annealing and
183. CVPR 2026R-C2 Cycle-Consistent Reinforcement Learning Improves Multimodal Reasoning
184. CVPR 2026R3-PCQA Ray-Reprojection-Reinforcement for No-Reference 3D Point Cloud Quality Assessment
185. CVPR 2026RawMetaDiff Unlocking Extreme Darkness from Dual-Exposure RAW with Meta-Guided Diffusion
186. CVPR 2026Reading or Reasoning Format Decoupled Reinforcement Learning for Document OCR
187. CVPR 2026ReAG Reasoning-Augmented Generation for Knowledge-based Visual Question Answering
188. CVPR 2026Real-Time Long Horizon Air Quality Forecasting via Group-Relative Policy Optimization
189. CVPR 2026RealUnify Do Unified Models Truly Benefit from Unification A Comprehensive
190. CVPR 2026Reasoning Palette Modulating Reasoning via Latent Contextualization for Controllable Exploration
191. CVPR 2026Reasoning-Driven Anomaly Detection and Localization with Image-Level Supervision
192. CVPR 2026RebRL Reinforcing Discrete Visual Diffusion Models with Rebalanced Timestep Credits
193. CVPR 2026Recovering Physically Plausible Human-Object Interactions from Monocular Videos
194. CVPR 2026Recurrent Reasoning with Vision-Language Models for Estimating Long-Horizon Embodied Task
195. CVPR 2026Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning
196. CVPR 2026RehearseVLA Simulated Post-Training for VLAs with Physically-Consistent World Model
197. CVPR 2026Reinforce to Learn Elect to Reason A Dual Paradigm for
198. CVPR 2026Reinforcing Structured Chain-of-Thought for Video Understanding
199. CVPR 2026Reinforcing Video Object Segmentation to Think before it Segments
200. CVPR 2026ReLaX Reasoning with Latent Exploration for Large Reasoning Models

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。