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 1 / 9 页

1. ICML 2025A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs
2. ICML 2025A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control
3. ICML 2025A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
4. ICML 2025A Mixed-Curvature based Pre-training Paradigm for Multi-Task Vehicle Routing Solver
5. ICML 2025A Model of Place Field Reorganization During Reward Maximization
6. ICML 2025A Multi-Region Brain Model to Elucidate the Role of Hippocampus in Spatially Embedded Decision-Making
7. ICML 2025A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous Systems
8. ICML 2025A Reduction Framework for Distributionally Robust Reinforcement Learning under Average Reward
9. ICML 2025A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents
10. ICML 2025A Sharper Global Convergence Analysis for Average Reward Reinforcement Learning via an Actor-Critic Approach
11. ICML 2025A Theoretical Justification for Asymmetric Actor-Critic Algorithms
12. ICML 2025A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization
13. ICML 2025A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO
14. ICML 2025Accelerating Quantum Reinforcement Learning with a Quantum Natural Policy Gradient Based Approach
15. ICML 2025Accurate and Efficient World Modeling with Masked Latent Transformers
16. ICML 2025Action-Constrained Imitation Learning
17. ICML 2025Action-Dependent Optimality-Preserving Reward Shaping
18. ICML 2025Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss
19. ICML 2025Active Fine-Tuning of Multi-Task Policies
20. ICML 2025Active Reward Modeling: Adaptive Preference Labeling for Large Language Model Alignment
21. ICML 2025Actor-Critics Can Achieve Optimal Sample Efficiency
22. ICML 2025Ad Hoc Teamwork via Offline Goal-Based Decision Transformers
23. ICML 2025Ad-Hoc Human-AI Coordination Challenge
24. ICML 2025Adaptive Exploration for Multi-Reward Multi-Policy Evaluation
25. ICML 2025Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection
26. ICML 2025ADDQ: Adaptive distributional double Q-learning
27. ICML 2025AdvAgent: Controllable Blackbox Red-teaming on Web Agents
28. ICML 2025Adversarial Inception Backdoor Attacks against Reinforcement Learning
29. ICML 2025Agent-Centric Actor-Critic for Asynchronous Multi-Agent Reinforcement Learning
30. ICML 2025AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N
31. ICML 2025Aligned Multi Objective Optimization
32. ICML 2025AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization
33. ICML 2025AlphaPO: Reward Shape Matters for LLM Alignment
34. ICML 2025AlphaQCM: Alpha Discovery in Finance with Distributional Reinforcement Learning
35. ICML 2025An Online Learning Approach to Prompt-based Selection of Generative Models and LLMs
36. ICML 2025An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints
37. ICML 2025Analytical Lyapunov Function Discovery: An RL-based Generative Approach
38. ICML 2025ARS: Adaptive Reward Scaling for Multi-Task Reinforcement Learning
39. ICML 2025AssistanceZero: Scalably Solving Assistance Games
40. ICML 2025AUTOCIRCUIT-RL: Reinforcement Learning-Driven LLM for Automated Circuit Topology Generation
41. ICML 2025Automatic Reward Shaping from Confounded Offline Data
42. ICML 2025Behavior-agnostic Task Inference for Robust Offline In-context Reinforcement Learning
43. ICML 2025Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning
44. ICML 2025Behavioral Exploration: Learning to Explore via In-Context Adaptation
45. ICML 2025Bellman Unbiasedness: Toward Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation
46. ICML 2025Benchmarking Quantum Reinforcement Learning
47. ICML 2025Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment
48. ICML 2025Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement Learning
49. ICML 2025Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC
50. ICML 2025Branches: Efficiently Seeking Optimal Sparse Decision Trees via AO*

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。