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 24 / 33 页

1151. NeurIPS 2025Improving Regret Approximation for Unsupervised Dynamic Environment Generation
1152. NeurIPS 2025Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning
1153. NeurIPS 2025Improving Reward Models with Proximal Policy Exploration for Preference-Based Reinforcement Learning
1154. NeurIPS 2025Improving Video Generation with Human Feedback
1155. NeurIPS 2025In-Context Fully Decentralized Cooperative Multi-Agent Reinforcement Learning
1156. NeurIPS 2025Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
1157. NeurIPS 2025Incentivizing LLMs to Self-Verify Their Answers
1158. NeurIPS 2025Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models
1159. NeurIPS 2025Incremental Sequence Classification with Temporal Consistency
1160. NeurIPS 2025Information-Theoretic Reward Decomposition for Generalizable RLHF
1161. NeurIPS 2025Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning
1162. NeurIPS 2025InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
1163. NeurIPS 2025Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Regularized Exploration in Reinforcement Learning
1164. NeurIPS 2025Intrinsic Goals for Autonomous Agents: Model-Based Exploration in Virtual Zebrafish Predicts Ethological Behavior and Whole-Brain Dynamics
1165. NeurIPS 2025Inverse Optimization Latent Variable Models for Learning Costs Applied to Route Problems
1166. NeurIPS 2025IOSTOM: Offline Imitation Learning from Observations via State Transition Occupancy Matching
1167. NeurIPS 2025Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs
1168. NeurIPS 2025Iterative Foundation Model Fine-Tuning on Multiple Rewards
1169. NeurIPS 2025Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning
1170. NeurIPS 2025Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning
1171. NeurIPS 2025KeeA*: Epistemic Exploratory A* Search via Knowledge Calibration
1172. NeurIPS 2025Kernel conditional tests from learning-theoretic bounds
1173. NeurIPS 2025Kinaema: a recurrent sequence model for memory and pose in motion
1174. NeurIPS 2025KL Penalty Control via Perturbation for Direct Preference Optimization
1175. NeurIPS 2025KL-Regularized RLHF with Multiple Reference Models: Exact Solutions and Sample Complexity
1176. NeurIPS 2025Knot So Simple: A Minimalistic Environment for Spatial Reasoning
1177. NeurIPS 2025Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering
1178. NeurIPS 2025KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation
1179. NeurIPS 2025KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning
1180. NeurIPS 2025KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills
1181. NeurIPS 2025LaRes: Evolutionary Reinforcement Learning with LLM-based Adaptive Reward Search
1182. NeurIPS 2025Large Language Models as End-to-end Combinatorial Optimization Solvers
1183. NeurIPS 2025Large language models can learn and generalize steganographic chain-of-thought under process supervision
1184. NeurIPS 2025Latent Chain-of-Thought for Visual Reasoning
1185. NeurIPS 2025Latent Mixture of Symmetries for Sample-Efficient Dynamic Learning
1186. NeurIPS 2025LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers
1187. NeurIPS 2025Learning and Planning Multi-Agent Tasks via an MoE-based World Model
1188. NeurIPS 2025Learning Dense Hand Contact Estimation from Imbalanced Data
1189. NeurIPS 2025Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning
1190. NeurIPS 2025Learning from A Single Markovian Trajectory: Optimality and Variance Reduction
1191. NeurIPS 2025Learning from Demonstrations via Capability-Aware Goal Sampling
1192. NeurIPS 2025Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models
1193. NeurIPS 2025Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization
1194. NeurIPS 2025Learning in Stackelberg Mean Field Games: A Non-Asymptotic Analysis
1195. NeurIPS 2025Learning Interactive World Model for Object-Centric Reinforcement Learning
1196. NeurIPS 2025Learning Interestingness in Automated Mathematical Theory Formation
1197. NeurIPS 2025Learning Intractable Multimodal Policies with Reparameterization and Diversity Regularization
1198. NeurIPS 2025Learning Memory-Enhanced Improvement Heuristics for Flexible Job Shop Scheduling
1199. NeurIPS 2025Learning Parameterized Skills from Demonstrations
1200. NeurIPS 2025Learning Personalized Ad Impact via Contextual Reinforcement Learning under Delayed Rewards

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。