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 356 篇，第 3 / 8 页

101. ICML 2024Fourier Controller Networks for Real-Time Decision-Making in Embodied Learning
102. ICML 2024From Biased Selective Labels to Pseudo-Labels: An Expectation-Maximization Framework for Learning from Biased Decisions
103. ICML 2024From Generalization Analysis to Optimization Designs for State Space Models
104. ICML 2024From Inverse Optimization to Feasibility to ERM
105. ICML 2024From Neurons to Neutrons: A Case Study in Interpretability
106. ICML 2024From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems
107. ICML 2024From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning
108. ICML 2024Fully-Dynamic Approximate Decision Trees With Worst-Case Update Time Guarantees
109. ICML 2024Fundamental Limitations of Alignment in Large Language Models
110. ICML 2024FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning
111. ICML 2024Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction
112. ICML 2024GFlowNet Training by Policy Gradients
113. ICML 2024Global Reinforcement Learning : Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods
114. ICML 2024Hard Tasks First: Multi-Task Reinforcement Learning Through Task Scheduling
115. ICML 2024HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning
116. ICML 2024HarmonyDream: Task Harmonization Inside World Models
117. ICML 2024HGAP: Boosting Permutation Invariant and Permutation Equivariant in Multi-Agent Reinforcement Learning via Graph Attention Network
118. ICML 2024HGCN2SP: Hierarchical Graph Convolutional Network for Two-Stage Stochastic Programming
119. ICML 2024Hieros: Hierarchical Imagination on Structured State Space Sequence World Models
120. ICML 2024How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?
121. ICML 2024How Does Goal Relabeling Improve Sample Efficiency?
122. ICML 2024How to Explore with Belief: State Entropy Maximization in POMDPs
123. ICML 2024How to Leverage Diverse Demonstrations in Offline Imitation Learning
124. ICML 2024Human Alignment of Large Language Models through Online Preference Optimisation
125. ICML 2024Hybrid Inverse Reinforcement Learning
126. ICML 2024Hybrid Reinforcement Learning from Offline Observation Alone
127. ICML 2024Implicit Bias of Policy Gradient in Linear Quadratic Control: Extrapolation to Unseen Initial States
128. ICML 2024Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements
129. ICML 2024Improving Generalization in Offline Reinforcement Learning via Adversarial Data Splitting
130. ICML 2024Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games
131. ICML 2024Improving Token-Based World Models with Parallel Observation Prediction
132. ICML 2024In value-based deep reinforcement learning, a pruned network is a good network
133. ICML 2024In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought
134. ICML 2024In-Context Learning Agents Are Asymmetric Belief Updaters
135. ICML 2024In-Context Reinforcement Learning for Variable Action Spaces
136. ICML 2024Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning
137. ICML 2024Inferring Dynamic Networks from Marginals with Iterative Proportional Fitting
138. ICML 2024Inferring the Long-Term Causal Effects of Long-Term Treatments from Short-Term Experiments
139. ICML 2024Information-Directed Pessimism for Offline Reinforcement Learning
140. ICML 2024Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning
141. ICML 2024INViT: A Generalizable Routing Problem Solver with Invariant Nested View Transformer
142. ICML 2024Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study
143. ICML 2024Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective
144. ICML 2024Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF
145. ICML 2024Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-constraint
146. ICML 2024Iterative Regularized Policy Optimization with Imperfect Demonstrations
147. ICML 2024Just Cluster It: An Approach for Exploration in High-Dimensions using Clustering and Pre-Trained Representations
148. ICML 2024LAGMA: LAtent Goal-guided Multi-Agent Reinforcement Learning
149. ICML 2024Langevin Policy for Safe Reinforcement Learning
150. ICML 2024Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game

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。