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 405 篇，第 4 / 9 页

151. ICML 2025Guided Zeroth-Order Methods for Stochastic Non-convex Problems with Decision-Dependent Distributions
152. ICML 2025Habitizing Diffusion Planning for Efficient and Effective Decision Making
153. ICML 2025Hierarchical Reinforcement Learning with Targeted Causal Interventions
154. ICML 2025Hierarchical Reinforcement Learning with Uncertainty-Guided Diffusional Subgoals
155. ICML 2025High-Dimensional Prediction for Sequential Decision Making
156. ICML 2025How does Labeling Error Impact Contrastive Learning? A Perspective from Data Dimensionality Reduction
157. ICML 2025HYGMA: Hypergraph Coordination Networks with Dynamic Grouping for Multi-Agent Reinforcement Learning
158. ICML 2025Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning
159. ICML 2025Hyperspherical Normalization for Scalable Deep Reinforcement Learning
160. ICML 2025IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic
161. ICML 2025Imitation Learning from a Single Temporally Misaligned Video
162. ICML 2025Improved Lower Bounds for First-order Stochastic Non-convex Optimization under Markov Sampling
163. ICML 2025Improved Off-policy Reinforcement Learning in Biological Sequence Design
164. ICML 2025Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces
165. ICML 2025Improving Reward Model Generalization from Adversarial Process Enhanced Preferences
166. ICML 2025Improving the Continuity of Goal-Achievement Ability via Policy Self-Regularization for Goal-Conditioned Reinforcement Learning
167. ICML 2025Improving Transformer World Models for Data-Efficient RL
168. ICML 2025Improving Value Estimation Critically Enhances Vanilla Policy Gradient
169. ICML 2025In-Context Reinforcement Learning From Suboptimal Historical Data
170. ICML 2025Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games
171. ICML 2025Inducing, Detecting and Characterising Neural Modules: A Pipeline for Functional Interpretability in Reinforcement Learning
172. ICML 2025Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces
173. ICML 2025Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviors
174. ICML 2025Investigating the Overlooked Hessian Structure: From CNNs to LLMs
175. ICML 2025Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
176. ICML 2025KEA: Keeping Exploration Alive by Proactively Coordinating Exploration Strategies
177. ICML 2025Knowledge Retention in Continual Model-Based Reinforcement Learning
178. ICML 2025LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimization
179. ICML 2025Language Models as Implicit Tree Search
180. ICML 2025LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence
181. ICML 2025Latent Action Learning Requires Supervision in the Presence of Distractors
182. ICML 2025Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models
183. ICML 2025LBI-FL: Low-Bit Integerized Federated Learning with Temporally Dynamic Bit-Width Allocation
184. ICML 2025Learning Dynamics under Environmental Constraints via Measurement-Induced Bundle Structures
185. ICML 2025Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-Network
186. ICML 2025Learning Fused State Representations for Control from Multi-View Observations
187. ICML 2025Learning Mean Field Control on Sparse Graphs
188. ICML 2025Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks
189. ICML 2025Learning Progress Driven Multi-Agent Curriculum
190. ICML 2025Learning to Reuse Policies in State Evolvable Environments
191. ICML 2025Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL
192. ICML 2025Learning Utilities from Demonstrations in Markov Decision Processes
193. ICML 2025Learning with Selectively Labeled Data from Multiple Decision-makers
194. ICML 2025Leveraging Offline Data in Linear Latent Contextual Bandits
195. ICML 2025Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration
196. ICML 2025Linear $Q$-Learning Does Not Diverge in $L^2$: Convergence Rates to a Bounded Set
197. ICML 2025LineFlow: A Framework to Learn Active Control of Production Lines
198. ICML 2025LipsNet++: Unifying Filter and Controller into a Policy Network
199. ICML 2025LLM Alignment as Retriever Optimization: An Information Retrieval Perspective
200. ICML 2025LLM-Assisted Semantically Diverse Teammate Generation for Efficient Multi-agent Coordination

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。