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 3 / 8 页

101. ICLR 2025Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Sampling
102. ICLR 2025Efficient Multi-agent Offline Coordination via Diffusion-based Trajectory Stitching
103. ICLR 2025Efficient Off-Policy Learning for High-Dimensional Action Spaces
104. ICLR 2025Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data
105. ICLR 2025Efficient Policy Evaluation with Safety Constraint for Reinforcement Learning
106. ICLR 2025Efficient Reinforcement Learning with Large Language Model Priors
107. ICLR 2025Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous Grasping
108. ICLR 2025Empowering LLM Agents with Zero-Shot Optimal Decision-Making through Q-learning
109. ICLR 2025Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference
110. ICLR 2025Energy-Weighted Flow Matching for Offline Reinforcement Learning
111. ICLR 2025Episodic Novelty Through Temporal Distance
112. ICLR 2025eQMARL: Entangled Quantum Multi-Agent Reinforcement Learning for Distributed Cooperation over Quantum Channels
113. ICLR 2025Evaluating Large Language Models through Role-Guide and Self-Reflection: A Comparative Study
114. ICLR 2025Expected Return Symmetries
115. ICLR 2025Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank
116. ICLR 2025Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
117. ICLR 2025Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning
118. ICLR 2025Fat-to-Thin Policy Optimization: Offline Reinforcement Learning with Sparse Policies
119. ICLR 2025Federated $Q$-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost
120. ICLR 2025Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset
121. ICLR 2025Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design
122. ICLR 2025First-Person Fairness in Chatbots
123. ICLR 2025Flat Reward in Policy Parameter Space Implies Robust Reinforcement Learning
124. ICLR 2025FlickerFusion: Intra-trajectory Domain Generalizing Multi-agent Reinforcement Learning
125. ICLR 2025Following the Human Thread in Social Navigation
126. ICLR 2025FOSP: Fine-tuning Offline Safe Policy through World Models
127. ICLR 2025From Attention to Activation: Unraveling the Enigmas of Large Language Models
128. ICLR 2025From Promise to Practice: Realizing High-performance Decentralized Training
129. ICLR 2025From Tokens to Words: On the Inner Lexicon of LLMs
130. ICLR 2025Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition
131. ICLR 2025GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-Time Alignment
132. ICLR 2025Generating Freeform Endoskeletal Robots
133. ICLR 2025Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces
134. ICLR 2025Geometry-aware RL for Manipulation of Varying Shapes and Deformable Objects
135. ICLR 2025Global Convergence of Policy Gradient in Average Reward MDPs
136. ICLR 2025GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS
137. ICLR 2025Grammar Reinforcement Learning: path and cycle counting in graphs with a Context-Free Grammar and Transformer approach
138. ICLR 2025Graph Assisted Offline-Online Deep Reinforcement Learning for Dynamic Workflow Scheduling
139. ICLR 2025GROOT-2: Weakly Supervised Multimodal Instruction Following Agents
140. ICLR 2025Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval
141. ICLR 2025Handling Delay in Real-Time Reinforcement Learning
142. ICLR 2025HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents
143. ICLR 2025HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning
144. ICLR 2025Hierarchical World Models as Visual Whole-Body Humanoid Controllers
145. ICLR 2025Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning
146. ICLR 2025Horizon Generalization in Reinforcement Learning
147. ICLR 2025How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?
148. ICLR 2025How Far Are We from True Unlearnability?
149. ICLR 2025How to Evaluate Reward Models for RLHF
150. ICLR 2025How to Find the Exact Pareto Front for Multi-Objective MDPs?

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。