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 2 / 8 页

51. ICLR 2025Can Reinforcement Learning Solve Asymmetric Combinatorial-Continuous Zero-Sum Games?
52. ICLR 2025Causal Information Prioritization for Efficient Reinforcement Learning
53. ICLR 2025Circuit Transformer: A Transformer That Preserves Logical Equivalence
54. ICLR 2025CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control
55. ICLR 2025COFlowNet: Conservative Constraints on Flows Enable High-Quality Candidate Generation
56. ICLR 2025Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
57. ICLR 2025ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization
58. ICLR 2025Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics
59. ICLR 2025Computing Circuits Optimization via Model-Based Circuit Genetic Evolution
60. ICLR 2025Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning
61. ICLR 2025Constraint-Conditioned Actor-Critic for Offline Safe Reinforcement Learning
62. ICLR 2025ContraDiff: Planning Towards High Return States via Contrastive Learning
63. ICLR 2025Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization
64. ICLR 2025Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking
65. ICLR 2025Counterfactual Realizability
66. ICLR 2025Cross-Domain Offline Policy Adaptation with Optimal Transport and Dataset Constraint
67. ICLR 2025Cross-Embodiment Dexterous Grasping with Reinforcement Learning
68. ICLR 2025CycleResearcher: Improving Automated Research via Automated Review
69. ICLR 2025DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control
70. ICLR 2025Data Center Cooling System Optimization Using Offline Reinforcement Learning
71. ICLR 2025Deep Networks Learn Features From Local Discontinuities in the Label Function
72. ICLR 2025DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL
73. ICLR 2025DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search
74. ICLR 2025DeLLMa: Decision Making Under Uncertainty with Large Language Models
75. ICLR 2025DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human References
76. ICLR 2025Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning
77. ICLR 2025Diffusion Models Are Real-Time Game Engines
78. ICLR 2025Diffusion Policy Policy Optimization
79. ICLR 2025Digi-Q: Learning VLM Q-Value Functions for Training Device-Control Agents
80. ICLR 2025Direct Distributional Optimization for Provable Alignment of Diffusion Models
81. ICLR 2025Discrete Codebook World Models for Continuous Control
82. ICLR 2025Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control
83. ICLR 2025Distilling Reinforcement Learning Algorithms for In-Context Model-Based Planning
84. ICLR 2025DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agent
85. ICLR 2025Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learning
86. ICLR 2025Diverse Preference Learning for Capabilities and Alignment
87. ICLR 2025Do WGANs succeed because they minimize the Wasserstein Distance? Lessons from Discrete Generators
88. ICLR 2025DoF: A Diffusion Factorization Framework for Offline Multi-Agent Reinforcement Learning
89. ICLR 2025Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL
90. ICLR 2025Doubly Optimal Policy Evaluation for Reinforcement Learning
91. ICLR 2025Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient
92. ICLR 2025DSPO: Direct Score Preference Optimization for Diffusion Model Alignment
93. ICLR 2025Dynamic Contrastive Skill Learning with State-Transition Based Skill Clustering and Dynamic Length Adjustment
94. ICLR 2025Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective
95. ICLR 2025Efficient Action-Constrained Reinforcement Learning via Acceptance-Rejection Method and Augmented MDPs
96. ICLR 2025Efficient Cross-Episode Meta-RL
97. ICLR 2025Efficient Discovery of Pareto Front for Multi-Objective Reinforcement Learning
98. ICLR 2025Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets
99. ICLR 2025Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction
100. ICLR 2025Efficient Imitation under Misspecification

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。