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 2 / 9 页

51. ICML 2025Breaking the Curse of Multiagency in Robust Multi-Agent Reinforcement Learning
52. ICML 2025BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning
53. ICML 2025C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation
54. ICML 2025C2IQL: Constraint-Conditioned Implicit Q-learning for Safe Offline Reinforcement Learning
55. ICML 2025Calibrated Value-Aware Model Learning with Probabilistic Environment Models
56. ICML 2025Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective
57. ICML 2025Catching Two Birds with One Stone: Reward Shaping with Dual Random Networks for Balancing Exploration and Exploitation
58. ICML 2025Categorical Distributional Reinforcement Learning with Kullback-Leibler Divergence: Convergence and Asymptotics
59. ICML 2025Catoni Contextual Bandits are Robust to Heavy-tailed Rewards
60. ICML 2025CERTAIN: Context Uncertainty-aware One-Shot Adaptation for Context-based Offline Meta Reinforcement Learning
61. ICML 2025Chip Placement with Diffusion Models
62. ICML 2025CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries
63. ICML 2025Clone-Robust AI Alignment
64. ICML 2025Closed-form Solutions: A New Perspective on Solving Differential Equations
65. ICML 2025CogReact: A Reinforced Framework to Model Human Cognitive Reaction Modulated by Dynamic Intervention
66. ICML 2025CollabLLM: From Passive Responders to Active Collaborators
67. ICML 2025Combinatorial Reinforcement Learning with Preference Feedback
68. ICML 2025Comparing Comparisons: Informative and Easy Human Feedback with Distinguishability Queries
69. ICML 2025Comparing Few to Rank Many: Active Human Preference Learning Using Randomized Frank-Wolfe Method
70. ICML 2025Concurrent Reinforcement Learning with Aggregated States via Randomized Least Squares Value Iteration
71. ICML 2025Consensus Based Stochastic Optimal Control
72. ICML 2025Conservative Offline Goal-Conditioned Implicit V-Learning
73. ICML 2025Constrain Alignment with Sparse Autoencoders
74. ICML 2025Constrained Exploitability Descent: An Offline Reinforcement Learning Method for Finding Mixed-Strategy Nash Equilibrium
75. ICML 2025Contextual Optimization Under Model Misspecification: A Tractable and Generalizable Approach
76. ICML 2025Continual Reinforcement Learning by Planning with Online World Models
77. ICML 2025Controlling Large Language Model with Latent Action
78. ICML 2025Controlling Underestimation Bias in Constrained Reinforcement Learning for Safe Exploration
79. ICML 2025Convergence Analysis of Policy Gradient Methods with Dynamic Stochasticity
80. ICML 2025Convergence of Policy Mirror Descent Beyond Compatible Function Approximation
81. ICML 2025Convex Markov Games: A New Frontier for Multi-Agent Reinforcement Learning
82. ICML 2025Counting atoms faster: policy-based nuclear magnetic resonance pulse sequencing for atomic abundance measurement
83. ICML 2025Craftium: Bridging Flexibility and Efficiency for Rich 3D Single- and Multi-Agent Environments
84. ICML 2025Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination
85. ICML 2025D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples
86. ICML 2025David and Goliath: Small One-step Model Beats Large Diffusion with Score Post-training
87. ICML 2025Decision Mixer: Integrating Long-term and Local Dependencies via Dynamic Token Selection for Decision-Making
88. ICML 2025Decoding Rewards in Competitive Games: Inverse Game Theory with Entropy Regularization
89. ICML 2025Deep Reinforcement Learning from Hierarchical Preference Design
90. ICML 2025Demonstration Selection for In-Context Learning via Reinforcement Learning
91. ICML 2025Demystifying Long Chain-of-Thought Reasoning
92. ICML 2025Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation
93. ICML 2025Design Considerations in Offline Preference-based RL
94. ICML 2025DiLQR: Differentiable Iterative Linear Quadratic Regulator via Implicit Differentiation
95. ICML 2025DiMa: Understanding the Hardness of Online Matching Problems via Diffusion Models
96. ICML 2025DIME: Diffusion-Based Maximum Entropy Reinforcement Learning
97. ICML 2025DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy
98. ICML 2025Directly Forecasting Belief for Reinforcement Learning with Delays
99. ICML 2025Discriminative Policy Optimization for Token-Level Reward Models
100. ICML 2025Distributionally Robust Multi-Agent Reinforcement Learning for Dynamic Chute Mapping

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。