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 1,190 篇，第 23 / 24 页

1101. NeurIPS 2024Sample-Efficient Agnostic Boosting
1102. NeurIPS 2024Sample-Efficient Constrained Reinforcement Learning with General Parameterization
1103. NeurIPS 2024SCAFFLSA: Taming Heterogeneity in Federated Linear Stochastic Approximation and TD Learning
1104. NeurIPS 2024Scalable and Effective Arithmetic Tree Generation for Adder and Multiplier Designs
1105. NeurIPS 2024Scalable Constrained Policy Optimization for Safe Multi-agent Reinforcement Learning
1106. NeurIPS 2024Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms
1107. NeurIPS 2024SCaR: Refining Skill Chaining for Long-Horizon Robotic Manipulation via Dual Regularization
1108. NeurIPS 2024SeeA*: Efficient Exploration-Enhanced A* Search by Selective Sampling
1109. NeurIPS 2024Seek Commonality but Preserve Differences: Dissected Dynamics Modeling for Multi-modal Visual RL
1110. NeurIPS 2024Self-Play Fine-tuning of Diffusion Models for Text-to-image Generation
1111. NeurIPS 2024Self-playing Adversarial Language Game Enhances LLM Reasoning
1112. NeurIPS 2024Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity
1113. NeurIPS 2024Shared Autonomy with IDA: Interventional Diffusion Assistance
1114. NeurIPS 2024Simplifying Constraint Inference with Inverse Reinforcement Learning
1115. NeurIPS 2024Simplifying Latent Dynamics with Softly State-Invariant World Models
1116. NeurIPS 2024SimPO: Simple Preference Optimization with a Reference-Free Reward
1117. NeurIPS 2024SkiLD: Unsupervised Skill Discovery Guided by Factor Interactions
1118. NeurIPS 2024Skill-aware Mutual Information Optimisation for Zero-shot Generalisation in Reinforcement Learning
1119. NeurIPS 2024SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents
1120. NeurIPS 2024Solving Minimum-Cost Reach Avoid using Reinforcement Learning
1121. NeurIPS 2024Solving Zero-Sum Markov Games with Continuous State via Spectral Dynamic Embedding
1122. NeurIPS 2024Span-Based Optimal Sample Complexity for Weakly Communicating and General Average Reward MDPs
1123. NeurIPS 2024Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication
1124. NeurIPS 2024Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees
1125. NeurIPS 2024Speculative Monte-Carlo Tree Search
1126. NeurIPS 2024SPO: Sequential Monte Carlo Policy Optimisation
1127. NeurIPS 2024SPRINQL: Sub-optimal Demonstrations driven Offline Imitation Learning
1128. NeurIPS 2024State Chrono Representation for Enhancing Generalization in Reinforcement Learning
1129. NeurIPS 2024State-free Reinforcement Learning
1130. NeurIPS 2024Statistical Efficiency of Distributional Temporal Difference Learning
1131. NeurIPS 2024Stepwise Alignment for Constrained Language Model Policy Optimization
1132. NeurIPS 2024Stress-Testing Capability Elicitation With Password-Locked Models
1133. NeurIPS 2024Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning
1134. NeurIPS 2024Subject-driven Text-to-Image Generation via Preference-based Reinforcement Learning
1135. NeurIPS 2024Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning
1136. NeurIPS 2024SurgicAI: A Hierarchical Platform for Fine-Grained Surgical Policy Learning and Benchmarking
1137. NeurIPS 2024SustainDC: Benchmarking for Sustainable Data Center Control
1138. NeurIPS 2024Swift Sampler: Efficient Learning of Sampler by 10 Parameters
1139. NeurIPS 2024Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scale
1140. NeurIPS 2024Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces
1141. NeurIPS 2024Team-Fictitious Play for Reaching Team-Nash Equilibrium in Multi-team Games
1142. NeurIPS 2024Temporal-Difference Learning Using Distributed Error Signals
1143. NeurIPS 2024Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning
1144. NeurIPS 2024Text-Aware Diffusion for Policy Learning
1145. NeurIPS 2024The Dormant Neuron Phenomenon in Multi-Agent Reinforcement Learning Value Factorization
1146. NeurIPS 2024The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning
1147. NeurIPS 2024The Importance of Online Data: Understanding Preference Fine-tuning via Coverage
1148. NeurIPS 2024The Ladder in Chaos: Improving Policy Learning by Harnessing the Parameter Evolving Path in A Low-dimensional Space
1149. NeurIPS 2024The Limits of Transfer Reinforcement Learning with Latent Low-rank Structure
1150. NeurIPS 2024The Power of Resets in Online Reinforcement Learning

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。