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 405 篇，第 3 / 9 页

101. ICML 2025Distributionally Robust Policy Learning under Concept Drifts
102. ICML 2025Diversifying Robot Locomotion Behaviors with Extrinsic Behavioral Curiosity
103. ICML 2025Diversity By Design: Leveraging Distribution Matching for Offline Model-Based Optimization
104. ICML 2025Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning
105. ICML 2025Diving into Self-Evolving Training for Multimodal Reasoning
106. ICML 2025Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective
107. ICML 2025DPO Meets PPO: Reinforced Token Optimization for RLHF
108. ICML 2025DSBRouter: End-to-end Global Routing via Diffusion Schr\"{o}dinger Bridge
109. ICML 2025EARL-BO: Reinforcement Learning for Multi-Step Lookahead, High-Dimensional Bayesian Optimization
110. ICML 2025Efficient Online Reinforcement Learning for Diffusion Policy
111. ICML 2025Efficient Skill Discovery via Regret-Aware Optimization
112. ICML 2025EGPlace: An Efficient Macro Placement Method via Evolutionary Search with Greedy Repositioning Guided Mutation
113. ICML 2025ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics
114. ICML 2025Eliciting Language Model Behaviors with Investigator Agents
115. ICML 2025Embedding Safety into RL: A New Take on Trust Region Methods
116. ICML 2025Empirical Design in Reinforcement Learning
117. ICML 2025Enabling Optimal Decisions in Rehearsal Learning under CARE Condition
118. ICML 2025Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration
119. ICML 2025Enhancing Decision-Making of Large Language Models via Actor-Critic
120. ICML 2025Enhancing Diversity In Parallel Agents: A Maximum State Entropy Exploration Story
121. ICML 2025Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language Models
122. ICML 2025Ergodic Generative Flows
123. ICML 2025EvoControl: Multi-Frequency Bi-Level Control for High-Frequency Continuous Control
124. ICML 2025EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration
125. ICML 2025Exact Recovery of Sparse Binary Vectors from Generalized Linear Measurements
126. ICML 2025Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal Representations
127. ICML 2025Explicit Exploration for High-Welfare Equilibria in Game-Theoretic Multiagent Reinforcement Learning
128. ICML 2025Explicit Preference Optimization: No Need for an Implicit Reward Model
129. ICML 2025Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher Sampling
130. ICML 2025Extreme Value Policy Optimization for Safe Reinforcement Learning
131. ICML 2025Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments
132. ICML 2025Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean Field Games
133. ICML 2025Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning
134. ICML 2025Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples
135. ICML 2025Flow Q-Learning
136. ICML 2025Flow-based Domain Randomization for Learning and Sequencing Robotic Skills
137. ICML 2025Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through Options
138. ICML 2025FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making
139. ICML 2025Gap-Dependent Bounds for Federated $Q$-Learning
140. ICML 2025General agents need world models
141. ICML 2025GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation
142. ICML 2025Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning
143. ICML 2025GoIRL: Graph-Oriented Inverse Reinforcement Learning for Multimodal Trajectory Prediction
144. ICML 2025Gradient Boosting Reinforcement Learning
145. ICML 2025GradPS: Resolving Futile Neurons in Parameter Sharing Network for Multi-Agent Reinforcement Learning
146. ICML 2025Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning
147. ICML 2025GRAM: A Generative Foundation Reward Model for Reward Generalization
148. ICML 2025Graph Diffusion for Robust Multi-Agent Coordination
149. ICML 2025Graph-Assisted Stitching for Offline Hierarchical Reinforcement Learning
150. ICML 2025Graph-Supported Dynamic Algorithm Configuration for Multi-Objective Combinatorial Optimization

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。