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 2 / 138 页

51. CVPR 2026Do Less Achieve More Do We Need Every-Step Optimization for
52. CVPR 2026DriveVLN Towards Mapless Vision-and-Language Navigation in Autonomous Driving
53. CVPR 2026DRM Diffusion-based Reward Model With Step-wise Guidance
54. CVPR 2026DSO Direct Steering Optimization for Bias Mitigation
55. CVPR 2026Dual-Agent Reinforcement Learning for Adaptive and Cost-Aware Visual-Inertial Odometry
56. CVPR 2026DualReg Dual-Space Filtering and Reinforcement for Rigid Registration
57. CVPR 2026Dynamic Important Example Mining for Reinforcement Finetuning
58. CVPR 2026EagleVision A Dual-Stage Framework with BEV-grounding-based Chain-of-Thought for Spatial Intelligence
59. CVPR 2026Easy2Hard From Partially to Fully Unmatched Modalities as Negative Samples
60. CVPR 2026Edges Compete for Trust Group Relative Edge Optimization for Building
61. CVPR 2026EE-RL Vision Language Guided Reinforcement Learning with Explorer and Expert
62. CVPR 2026Efficient Frame Selection for Long Video Understanding via Reinforcement Learning
63. CVPR 2026Electromagnetic Inverse Scattering from a Single Transmitter
64. CVPR 2026Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching
65. CVPR 2026ELV-Halluc Benchmarking Semantic Aggregation Hallucinations in Video Understanding
66. CVPR 2026EMO-R3 Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large
67. CVPR 2026Enhancing Spatial Understanding in Image Generation via Reward Modeling
68. CVPR 2026Enhancing Video Vision Language Model with Hippocampal Sensing
69. CVPR 2026EVA Efficient Reinforcement Learning for End-to-End Video Agent
70. CVPR 2026EvoGraph-R1 Self-Evolving Multimodal Knowledge Hypergraphs for Agentic Retrieval
71. CVPR 2026EvoID Reinforced Evolution for Identity-Preserving Video Generation
72. CVPR 2026Explore with Long-term Memory A Benchmark and Multimodal LLM-based Reinforcement
73. CVPR 2026Fine-Grained GRPO for Precise Preference Alignment in Flow Models
74. CVPR 2026FinPercep-RM A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based
75. CVPR 2026FireScope Wildfire Risk Raster Prediction With a Chain-of-Thought Oracle
76. CVPR 2026Flash-DMD Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and
77. CVPR 2026ForeHOI Feed-forward 3D Object Reconstruction from Daily Hand-Object Interaction Videos
78. CVPR 2026From Exploration to Exploitation A Two-Stage Entropy RLVR Approach for
79. CVPR 2026From Failure to Feedback Group Revision Unlocks Hard Cases in
80. CVPR 2026From Pairs to Sequences Track-Aware Policy Gradients for Keypoint Detection
81. CVPR 2026FUN REC Reconstructing Functional 3D Scenes from Egocentric Interaction
82. CVPR 2026GDPO-SR Group Direct Preference Optimization for One-Step Generative Image Super-Resolution
83. CVPR 2026GDRO Group-level Reward Post-training Suitable for Diffusion Models
84. CVPR 2026GenBreak Red Teaming Text-to-Image Generation Using Large Language Models
85. CVPR 2026General Process Reward Modeling for Robotic Reinforcement Learning
86. CVPR 2026GeoSANE Learning Geospatial Representations from Models Not Data
87. CVPR 2026GeoWorld Geometric World Models
88. CVPR 2026Global Underwater Geolocation from Time-Lapse Polarization Imagery
89. CVPR 2026Globally Optimal Pose from Orthographic Silhouettes
90. CVPR 2026Glove2Hand Synthesizing Natural Hand-Object Interaction from Multi-Modal Sensing Gloves
91. CVPR 2026GlyphPrinter Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering
92. CVPR 2026Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning
93. CVPR 2026Grounding Everything in Tokens for Multimodal Large Language Models
94. CVPR 2026GRPO-Guard Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping
95. CVPR 2026GThinker Towards General Multimodal Reasoning via Cue-Guided Rethinking
96. CVPR 2026GTR-Turbo Merged Checkpoint is Secretly a Free Teacher for Agentic
97. CVPR 2026GUI-SAGE Enhancing GUI Automation with Self-Explanatory Learning
98. CVPR 2026Harnessing Chain-of-Thought Reasoning in Multimodal Large Language Models for Face
99. CVPR 2026HDR-VLM HDR-Domain Adaptation of VLMs and Preference-Aligned Quality Assessment for
100. CVPR 2026Heuristic Self-Paced Learning for Domain Adaptive Semantic Segmentation under Adverse

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。