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 1 / 8 页

1. ICLR 2025$\phi$-Update: A Class of Policy Update Methods with Policy Convergence Guarantee
2. ICLR 2025$q$-exponential family for policy optimization
3. ICLR 20253DMolFormer: A Dual-channel Framework for Structure-based Drug Discovery
4. ICLR 2025A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety
5. ICLR 2025A Causal Lens for Learning Long-term Fair Policies
6. ICLR 2025A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement
7. ICLR 2025A Distributional Approach to Uncertainty-Aware Preference Alignment Using Offline Demonstrations
8. ICLR 2025A Generalist Hanabi Agent
9. ICLR 2025A Policy-Gradient Approach to Solving Imperfect-Information Games with Best-Iterate Convergence
10. ICLR 2025A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals
11. ICLR 2025A Theoretical Framework for Partially-Observed Reward States in RLHF
12. ICLR 2025Accelerating Goal-Conditioned Reinforcement Learning Algorithms and Research
13. ICLR 2025Accelerating Task Generalisation with Multi-Level Skill Hierarchies
14. ICLR 2025Accelerating Training with Neuron Interaction and Nowcasting Networks
15. ICLR 2025Action abstractions for amortized sampling
16. ICLR 2025Actions Speak Louder Than Words: Rate-Reward Trade-off in Markov Decision Processes
17. ICLR 2025ACTIVE: Offline Reinforcement Learning via Adaptive Imitation and In-sample $V$-Ensemble
18. ICLR 2025ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning
19. ICLR 2025Ada-K Routing: Boosting the Efficiency of MoE-based LLMs
20. ICLR 2025Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning
21. ICLR 2025Adaptive Gradient Clipping for Robust Federated Learning
22. ICLR 2025Adaptive teachers for amortized samplers
23. ICLR 2025AdaWM: Adaptive World Model based Planning for Autonomous Driving
24. ICLR 2025Adding Conditional Control to Diffusion Models with Reinforcement Learning
25. ICLR 2025Advantage Alignment Algorithms
26. ICLR 2025Adversarial Generative Flow Network for Solving Vehicle Routing Problems
27. ICLR 2025Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning
28. ICLR 2025AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation
29. ICLR 2025Aligning Visual Contrastive learning models via Preference Optimization
30. ICLR 2025An Evolved Universal Transformer Memory
31. ICLR 2025An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning
32. ICLR 2025Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning
33. ICLR 2025As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss
34. ICLR 2025Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis
35. ICLR 2025Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models
36. ICLR 2025BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games
37. ICLR 2025BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping
38. ICLR 2025Behavioral Entropy-Guided Dataset Generation for Offline Reinforcement Learning
39. ICLR 2025Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration
40. ICLR 2025Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models
41. ICLR 2025Bisimulation Metric for Model Predictive Control
42. ICLR 2025BlendRL: A Framework for Merging Symbolic and Neural Policy Learning
43. ICLR 2025BodyGen: Advancing Towards Efficient Embodiment Co-Design
44. ICLR 2025BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RL
45. ICLR 2025BOND: Aligning LLMs with Best-of-N Distillation
46. ICLR 2025Bootstrapped Model Predictive Control
47. ICLR 2025Bootstrapping Language Models with DPO Implicit Rewards
48. ICLR 2025Brain Bandit: A Biologically Grounded Neural Network for Efficient Control of Exploration
49. ICLR 2025BTBS-LNS: Binarized-Tightening, Branch and Search on Learning LNS Policies for MIP
50. ICLR 2025Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning

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。