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 1,827 篇，第 2 / 37 页

51. ICLR 2026ARROW: An Adaptive Rollout and Routing Method for Global Weather Forecasting
52. ICLR 2026ArtVIP: Articulated Digital Assets of Visual Realism, Modular Interaction, and Physical Fidelity for Robot Learning
53. ICLR 2026Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning
54. ICLR 2026Asynchronous Policy Gradient Aggregation for Efficient Distributed Reinforcement Learning
55. ICLR 2026ATGen: Adversarial Reinforcement Learning for Test Case Generation
56. ICLR 2026ATPO: ADAPTIVE TREE POLICY OPTIMIZATION FOR MULTI-TURN MEDICAL DIALOGUE
57. ICLR 2026Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
58. ICLR 2026AttriCtrl: A Generalizable Framework for Controlling Semantic Attribute Intensity in Diffusion Models
59. ICLR 2026Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models
60. ICLR 2026AutoDrive-R²: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving
61. ICLR 2026Automating the Refinement of Reinforcement Learning Specifications
62. ICLR 2026AutoQD: Automatic Discovery of Diverse Behaviors with Quality-Diversity Optimization
63. ICLR 2026AutoTool: Automatic Scaling of Tool-Use Capabilities in RL via Decoupled Entropy Constraints
64. ICLR 2026AWM: Accurate Weight-Matrix Fingerprint for Large Language Models
65. ICLR 2026Balancing the Experts: Unlocking LoRA-MoE for GRPO via Mechanism-Aware Rewards
66. ICLR 2026BaseReward: A Strong Baseline for Multimodal Reward Model
67. ICLR 2026Bayes Adaptive Monte Carlo Tree Search for Offline Model-based Reinforcement Learning
68. ICLR 2026Bayesian Ensemble for Sequential Decision-Making
69. ICLR 2026Bayesian Robust Cooperative Multi-Agent Reinforcement Learning Against Unknown Adversaries
70. ICLR 2026Belief-Based Offline Reinforcement Learning for Delay-Robust Policy Optimization
71. ICLR 2026Benchmarking Multi-Agent Reinforcement Learning in Power Grid Operations
72. ICLR 2026Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective
73. ICLR 2026Better Bounds for the Distributed Experts Problem
74. ICLR 2026Beware Untrusted Simulators -- Reward-Free Backdoor Attacks in Reinforcement Learning
75. ICLR 2026Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty
76. ICLR 2026Beyond Distributions: Geometric Action Control for Continuous Reinforcement Learning
77. ICLR 2026Beyond English-Centric Training: How Reinforcement Learning Improves Cross-Lingual Reasoning in LLMs
78. ICLR 2026Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE
79. ICLR 2026Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning
80. ICLR 2026Beyond Noisy-TVs: Noise-Robust Exploration Via Learning Progress Monitoring
81. ICLR 2026Beyond Pass@ 1: Self-Play with Variational Problem Synthesis Sustains RLVR
82. ICLR 2026Beyond Penalization: Diffusion-based Out-of-Distribution Detection and Selective Regularization in Offline Reinforcement Learning
83. ICLR 2026Beyond RLHF and NLHF: Population-Proportional Alignment under an Axiomatic Framework
84. ICLR 2026Beyond Simple Graphs: Neural Multi-Objective Routing on Multigraphs
85. ICLR 2026Beyond Softmax and Entropy: Convergence Rates of Policy Gradients with $\boldsymbol{f}$-SoftArgmax Parameterization $\&$ Coupled Regularization
86. ICLR 2026BFM-Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning
87. ICLR 2026Boolean Satisfiability via Imitation Learning
88. ICLR 2026Boosting Multi-Domain Reasoning of LLMs via Curvature-Guided Policy Optimization
89. ICLR 2026BoreaRL: A Multi-Objective Reinforcement Learning Environment for Climate-Adaptive Boreal Forest Management
90. ICLR 2026BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement Finetuning
91. ICLR 2026Bradley-Terry and Multi-Objective Reward Modeling Are Complementary
92. ICLR 2026Breaking Barriers: Do Reinforcement Fine-tuning Gains Transfer To Unseen Domains?
93. ICLR 2026Breaking Safety Paradox with Feasible Dual Policy Iteration
94. ICLR 2026Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation
95. ICLR 2026Breaking the Total Variance Barrier: Sharp Sample Complexity for Linear Heteroscedastic Bandits with Fixed Action Set
96. ICLR 2026BRIDGE: Bi-level Reinforcement Learning for Dynamic Group Structure in Coalition Formation Games
97. ICLR 2026Bridging Draft Policy Misalignment: Group Tree Optimization for Speculative Decoding
98. ICLR 2026Bridging Successor Measure and Online Policy Learning with Flow Matching-Based Representations
99. ICLR 2026Bridging the performance-gap between target-free and target-based reinforcement learning
100. ICLR 2026Buffer Matters: Unleashing the Power of Off-Policy Reinforcement Learning in Large Language Model Reasoning

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。