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 784 篇，第 1 / 16 页

1. NeurIPS 2025$\texttt{G1}$: Teaching LLMs to Reason on Graphs with Reinforcement Learning
2. NeurIPS 2025$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training
3. NeurIPS 20251000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities
4. NeurIPS 2025A Bayesian Fast-Slow Framework to Mitigate Interference in Non-Stationary Reinforcement Learning
5. NeurIPS 2025A Clean Slate for Offline Reinforcement Learning
6. NeurIPS 2025A Closer Look to Positive-Unlabeled Learning from Fine-grained Perspectives: An Empirical Study
7. NeurIPS 2025A Differential and Pointwise Control Approach to Reinforcement Learning
8. NeurIPS 2025A Finite Sample Analysis of Distributional TD Learning with Linear Function Approximation
9. NeurIPS 2025A Generalized Bisimulation Metric of State Similarity between Markov Decision Processes: From Theoretical Propositions to Applications
10. NeurIPS 2025A multiscale analysis of mean-field transformers in the moderate interaction regime
11. NeurIPS 2025A Novel General Framework for Sharp Lower Bounds in Succinct Stochastic Bandits
12. NeurIPS 2025A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning
13. NeurIPS 2025A Principled Path to Fitted Distributional Evaluation
14. NeurIPS 2025A Provable Approach for End-to-End Safe Reinforcement Learning
15. NeurIPS 2025A Reinforcement Learning-based Bidding Strategy for Data Consumers in Auction-based Federated Learning
16. NeurIPS 2025A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search
17. NeurIPS 2025A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning
18. NeurIPS 2025A Temporal Difference Method for Stochastic Continuous Dynamics
19. NeurIPS 2025A Theory for Worst-Case vs. Average-Case Guarantees for LLMs
20. NeurIPS 2025A Unifying View of Linear Function Approximation in Off-Policy RL Through Matrix Splitting and Preconditioning
21. NeurIPS 2025Absolute Zero: Reinforced Self-play Reasoning with Zero Data
22. NeurIPS 2025Accelerating RL for LLM Reasoning with Optimal Advantage Regression
23. NeurIPS 2025Accelerating Visual-Policy Learning through Parallel Differentiable Simulation
24. NeurIPS 2025AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning
25. NeurIPS 2025Achieving $\tilde{\mathcal{O}}(1/N)$ Optimality Gap in Restless Bandits through Gaussian Approximation
26. NeurIPS 2025Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
27. NeurIPS 2025Act to See, See to Act: Diffusion-Driven Perception-Action Interplay for Adaptive Policies
28. NeurIPS 2025Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models
29. NeurIPS 2025Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models
30. NeurIPS 2025ActiveVOO: Value of Observation Guided Active Knowledge Acquisition for Open-World Embodied Lifted Regression Planning
31. NeurIPS 2025Actor-Free Continuous Control via Structurally Maximizable Q-Functions
32. NeurIPS 2025Adaptable Safe Policy Learning from Multi-task Data with Constraint Prioritized Decision Transformer
33. NeurIPS 2025Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback
34. NeurIPS 2025Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization
35. NeurIPS 2025Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning
36. NeurIPS 2025Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models
37. NeurIPS 2025Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning
38. NeurIPS 2025Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural Networks
39. NeurIPS 2025Adaptive Variance Inflation in Thompson Sampling: Efficiency, Safety, Robustness, and Beyond
40. NeurIPS 2025Adaptively Coordinating with Novel Partners via Learned Latent Strategies
41. NeurIPS 2025AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking
42. NeurIPS 2025ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning
43. NeurIPS 2025Adversarial Diffusion for Robust Reinforcement Learning
44. NeurIPS 2025Adversarial Locomotion and Motion Imitation for Humanoid Policy Learning
45. NeurIPS 2025AegisGuard: RL-Guided Adapter Tuning for TEE-Based Efficient & Secure On-Device Inference
46. NeurIPS 2025Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization
47. NeurIPS 2025Agentic RL Scaling Law: Spontaneous Code Execution for Mathematical Problem Solving
48. NeurIPS 2025Align-DA: Align Score-based Atmospheric Data Assimilation with Multiple Preferences
49. NeurIPS 2025Aligning Transformers with Continuous Feedback via Energy Rank Alignment
50. NeurIPS 2025ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisition

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。