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 379 篇，第 4 / 8 页

151. ICLR 2025Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors
152. ICLR 2025HyPoGen: Optimization-Biased Hypernetworks for Generalizable Policy Generation
153. ICLR 2025Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models
154. ICLR 2025Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models
155. ICLR 2025Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought Leaps
156. ICLR 2025INS: Interaction-aware Synthesis to Enhance Offline Multi-agent Reinforcement Learning
157. ICLR 2025Integral Performance Approximation for Continuous-Time Reinforcement Learning Control
158. ICLR 2025Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models
159. ICLR 2025Interpreting Emergent Planning in Model-Free Reinforcement Learning
160. ICLR 2025IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning
161. ICLR 2025InvestESG: A multi-agent reinforcement learning benchmark for studying climate investment as a social dilemma
162. ICLR 2025Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision
163. ICLR 2025Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning
164. ICLR 2025Joint Reward and Policy Learning with Demonstrations and Human Feedback Improves Alignment
165. ICLR 2025Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks
166. ICLR 2025Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning
167. ICLR 2025Language Guided Skill Discovery
168. ICLR 2025Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning
169. ICLR 2025Lean-STaR: Learning to Interleave Thinking and Proving
170. ICLR 2025Learn Your Reference Model for Real Good Alignment
171. ICLR 2025Learning a Fast Mixing Exogenous Block MDP using a Single Trajectory
172. ICLR 2025Learning Continually by Spectral Regularization
173. ICLR 2025Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning
174. ICLR 2025Learning from negative feedback, or positive feedback or both
175. ICLR 2025Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation
176. ICLR 2025Learning mirror maps in policy mirror descent
177. ICLR 2025Learning on One Mode: Addressing Multi-modality in Offline Reinforcement Learning
178. ICLR 2025Learning Robust Representations with Long-Term Information for Generalization in Visual Reinforcement Learning
179. ICLR 2025Learning Splitting Heuristics in Divide-and-Conquer SAT Solvers with Reinforcement Learning
180. ICLR 2025Learning Task Belief Similarity with Latent Dynamics for Meta-Reinforcement Learning
181. ICLR 2025Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training
182. ICLR 2025Learning to Communicate Through Implicit Communication Channels
183. ICLR 2025Learning to Search from Demonstration Sequences
184. ICLR 2025Learning to Select Nodes in Branch and Bound with Sufficient Tree Representation
185. ICLR 2025Learning to Steer Markovian Agents under Model Uncertainty
186. ICLR 2025Learning Transformer-based World Models with Contrastive Predictive Coding
187. ICLR 2025Learning View-invariant World Models for Visual Robotic Manipulation
188. ICLR 2025Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning
189. ICLR 2025Leveraging Variable Sparsity to Refine Pareto Stationarity in Multi-Objective Optimization
190. ICLR 2025LICORICE: Label-Efficient Concept-Based Interpretable Reinforcement Learning
191. ICLR 2025Linear Multistep Solver Distillation for Fast Sampling of Diffusion Models
192. ICLR 2025Long-Short Decision Transformer: Bridging Global and Local Dependencies for Generalized Decision-Making
193. ICLR 2025Looking Backward: Retrospective Backward Synthesis for Goal-Conditioned GFlowNets
194. ICLR 2025Looking into User’s Long-term Interests through the Lens of Conservative Evidential Learning
195. ICLR 2025M^3PC: Test-time Model Predictive Control using Pretrained Masked Trajectory Model
196. ICLR 2025MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions
197. ICLR 2025MA$^2$E: Addressing Partial Observability in Multi-Agent Reinforcement Learning with Masked Auto-Encoder
198. ICLR 2025MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL
199. ICLR 2025MaestroMotif: Skill Design from Artificial Intelligence Feedback
200. ICLR 2025Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment

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。