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 4 / 33 页

151. ICLR 2025Digi-Q: Learning VLM Q-Value Functions for Training Device-Control Agents
152. ICLR 2025Direct Distributional Optimization for Provable Alignment of Diffusion Models
153. ICLR 2025Discrete Codebook World Models for Continuous Control
154. ICLR 2025Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control
155. ICLR 2025Distilling Reinforcement Learning Algorithms for In-Context Model-Based Planning
156. ICLR 2025DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agent
157. ICLR 2025Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learning
158. ICLR 2025Diverse Preference Learning for Capabilities and Alignment
159. ICLR 2025Do WGANs succeed because they minimize the Wasserstein Distance? Lessons from Discrete Generators
160. ICLR 2025DoF: A Diffusion Factorization Framework for Offline Multi-Agent Reinforcement Learning
161. ICLR 2025Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL
162. ICLR 2025Doubly Optimal Policy Evaluation for Reinforcement Learning
163. ICLR 2025Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient
164. ICLR 2025DSPO: Direct Score Preference Optimization for Diffusion Model Alignment
165. ICLR 2025Dynamic Contrastive Skill Learning with State-Transition Based Skill Clustering and Dynamic Length Adjustment
166. ICLR 2025Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective
167. ICLR 2025Efficient Action-Constrained Reinforcement Learning via Acceptance-Rejection Method and Augmented MDPs
168. ICLR 2025Efficient Cross-Episode Meta-RL
169. ICLR 2025Efficient Discovery of Pareto Front for Multi-Objective Reinforcement Learning
170. ICLR 2025Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets
171. ICLR 2025Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction
172. ICLR 2025Efficient Imitation under Misspecification
173. ICLR 2025Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Sampling
174. ICLR 2025Efficient Multi-agent Offline Coordination via Diffusion-based Trajectory Stitching
175. ICLR 2025Efficient Off-Policy Learning for High-Dimensional Action Spaces
176. ICLR 2025Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data
177. ICLR 2025Efficient Policy Evaluation with Safety Constraint for Reinforcement Learning
178. ICLR 2025Efficient Reinforcement Learning with Large Language Model Priors
179. ICLR 2025Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous Grasping
180. ICLR 2025Empowering LLM Agents with Zero-Shot Optimal Decision-Making through Q-learning
181. ICLR 2025Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference
182. ICLR 2025Energy-Weighted Flow Matching for Offline Reinforcement Learning
183. ICLR 2025Episodic Novelty Through Temporal Distance
184. ICLR 2025eQMARL: Entangled Quantum Multi-Agent Reinforcement Learning for Distributed Cooperation over Quantum Channels
185. ICLR 2025Evaluating Large Language Models through Role-Guide and Self-Reflection: A Comparative Study
186. ICLR 2025Expected Return Symmetries
187. ICLR 2025Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank
188. ICLR 2025Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
189. ICLR 2025Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning
190. ICLR 2025Fat-to-Thin Policy Optimization: Offline Reinforcement Learning with Sparse Policies
191. ICLR 2025Federated $Q$-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost
192. ICLR 2025Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset
193. ICLR 2025Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design
194. ICLR 2025First-Person Fairness in Chatbots
195. ICLR 2025Flat Reward in Policy Parameter Space Implies Robust Reinforcement Learning
196. ICLR 2025FlickerFusion: Intra-trajectory Domain Generalizing Multi-agent Reinforcement Learning
197. ICLR 2025Following the Human Thread in Social Navigation
198. ICLR 2025FOSP: Fine-tuning Offline Safe Policy through World Models
199. ICLR 2025From Attention to Activation: Unraveling the Enigmas of Large Language Models
200. ICLR 2025From Promise to Practice: Realizing High-performance Decentralized Training

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。