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 6,885 篇，第 3 / 138 页

101. CVPR 2026HiCoGen Hierarchical Compositional Text-to-Image Generation in Diffusion Models via Reinforcement
102. CVPR 2026HiconAgent History Context-aware Policy Optimization for GUI Agents
103. CVPR 2026Hierarchical Process Reward Models are Symbolic Vision Learners
104. CVPR 2026HP-Edit A Human-Preference Post-Training Framework for Image Editing
105. CVPR 2026HSI-GPT2 A Dual-Granularity Large Motion Reasoning Model with Diffusion Refinement
106. CVPR 2026HTNav A Hybrid Navigation Framework with Tiered Structure for Urban
107. CVPR 2026ID-Crafter VLM-Grounded Online RL for Compositional Multi-Subject Video Generation
108. CVPR 2026Identity-Preserving Image-to-Video Generation via Reward-Guided Optimization
109. CVPR 2026Image Diffusion Preview with Consistency Solver
110. CVPR 2026Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards
111. CVPR 2026Improving Vision-language Models with Perception-centric Process Reward Models
112. CVPR 2026Incentivizing Generative Zero-Shot Learning via Outcome-Reward Reinforcement Learning with Visual
113. CVPR 2026Incentivizing Versatile Video Reasoning in MLLMs via Data-Efficient Reinforcement Learning
114. CVPR 2026InterPrior Scaling Generative Control for Physics-Based Human-Object Interactions
115. CVPR 2026JoPPO Hierarchical Photography Assessment via Contrastive Joint Conditional Probabilistic Reinforcement
116. CVPR 2026Label What Matters Modality-Balanced and Difficulty-Aware Multimodal Active Learning
117. CVPR 2026LAOF Robust Latent Action Learning with Optical Flow Constraints
118. CVPR 2026Latent Chain-of-Thought World Modeling for End-to-End Autonomous Driving
119. CVPR 2026Learning a Unified Latent Action Space from Videos with Action-centric
120. CVPR 2026Learning from Synthetic Data via Provenance-Based Input Gradient Guidance
121. CVPR 2026Learning Personalized Photographic Style from Pairwise User Preferences
122. CVPR 2026Learning to Assist Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning
123. CVPR 2026Learning to Diversify and Focus A Reinforcement Framework for Open-Vocabulary
124. CVPR 2026Learning to Focus and Precise CroppingA Reinforcement Learning Framework with
125. CVPR 2026Learning to Generate via Understanding Understanding-Driven Intrinsic Rewarding for Unified
126. CVPR 2026Learning to Refuse Refusal-Aware Reinforcement Fine-Tuning for Hard-Irrelevant Queries in
127. CVPR 2026Learning to Select Visual Tools from Experience
128. CVPR 2026Learning What Helps Task-Aligned Context Selection for Vision Tasks
129. CVPR 2026Let VLMs Grade Their Own Thoughts A Self-Quantification Approach to
130. CVPR 2026Leveraging Verifier-Based Reinforcement Learning in Image Editing
131. CVPR 2026Linear Fundamental Matrix Estimation from 7 or 5 Points
132. CVPR 2026Linking Perception Confidence and Accuracy in MLLMs
133. CVPR 2026Local Motion Matters A Deconstruct-Recompose Paradigm for Reinforcement Learning Pre-training
134. CVPR 2026LongVideo-R1 Smart Navigation for Low-cost Long Video Understanding
135. CVPR 2026LongVT Incentivizing Thinking with Long Videos via Native Tool Calling
136. CVPR 2026Machine Mental Imagery Empower Multimodal Reasoning with Latent Visual Tokens
137. CVPR 2026MangoBench A Benchmark for Multi-Agent Goal-Conditioned Offline Reinforcement Learning
138. CVPR 2026MapReduce LoRA Advancing the Pareto Front in Multi-Preference Optimization for
139. CVPR 2026Masked Auto-Regressive Variational Acceleration Fast Inference Makes Practical Reinforcement Learning
140. CVPR 2026MaskFocus Focusing Policy Optimization on Critical Steps for Masked Image
141. CVPR 2026Masking Teacher and Reinforcing Student for Distilling Vision-Language Models
142. CVPR 2026MedGRPO Multi-Task Reinforcement Learning for Heterogeneous Medical Video Understanding
143. CVPR 2026MedLoc-R1 Performance-Aware Curriculum Reward Scheduling for GRPO-Based Medical Visual Grounding
144. CVPR 2026MedMO Grounding and Understanding Multimodal Large Language Model for Medical
145. CVPR 2026Mesh-Pro Asynchronous Advantage-guided Ranking Preference Optimization for Artist-style Quadrilateral Mesh
146. CVPR 2026Mimic Human Cognition Master Multi-Image Reasoning A Meta-Action Framework for
147. CVPR 2026MiniCPM-V 4.5 Cooking Efficient MLLMs via Architecture Data and Training
148. CVPR 2026MM-ReCoder Advancing Chart-to-Code Generation with Reinforcement Learning and Self-Correction
149. CVPR 2026MMR-AD A Large-Scale Multimodal Dataset for Benchmarking General Anomaly Detection
150. CVPR 2026MoE-GRPO Optimizing Mixture-of-Experts via Reinforcement Learning in Vision-Language Models

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。