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 2,494 篇，第 1 / 50 页

1. NeurIPS 2026\texttt{FEROM}: Frontier Endogenous Reveal-Order Marginal Policy Optimization for Masked Diffusion LMs
2. NeurIPS 2026$\gamma$-weakly $\theta$-up-concavity: A Unified Framework for Non-Convex Optimization Beyond DR-Submodular and OSS Functions
3. NeurIPS 2026$\varphi$TD: Distributional Reinforcement Learning using Characteristic Functions
4. NeurIPS 2026$f$-GRPO & Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment
5. NeurIPS 2026$R^2E$: A Role-driven Reward Evolutionary Framework for Automated Reward Function Design
6. NeurIPS 20262-Step Agent: How a Bayesian Decision Maker Learns from AI-Decision Support
7. NeurIPS 2026A Computational Perspective to Data Ablation Experiments
8. NeurIPS 2026A Constrained Bi-level Optimization Framework for Constrained Preference-Based Reinforcement Learning
9. NeurIPS 2026A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training
10. NeurIPS 2026A Geometric Perspective on Reward Function Updates in Inverse Reinforcement Learning
11. NeurIPS 2026A latent control model for realistic rodent motion
12. NeurIPS 2026A Model of Diverse Sampling from Language Models
13. NeurIPS 2026A New Framework for Quantum Reinforcement Learning
14. NeurIPS 2026A Primal-dual Approach for Semi-Infinitely Constrained Reinforcement Learning
15. NeurIPS 2026A Systematic Evaluation of Co-folding Model Representations for Small-Molecule Learning
16. NeurIPS 2026A$^2$IQL: Adaptive Asymmetric Implicit Q Learning for Automated Warehouse Consolidation
17. NeurIPS 2026AbFlowNet: Optimizing Antibody-Antigen Binding Energy via Diffusion-GFlowNet Fusion
18. NeurIPS 2026Absolute State-wise Constrained Policy Optimization: High-Probability State-wise Constraints Satisfaction
19. NeurIPS 2026Accelerating Safe Reinforcement Learning with Massive Parallelism
20. NeurIPS 2026ACQueReLlo: Alignment-Aware Constrained Quantization via Reinforcement Learning for Large Language Models
21. NeurIPS 2026Actor-Accelerated Policy Dual Averaging for Reinforcement Learning in Continuous Action Spaces
22. NeurIPS 2026Ad-Hoc Teamwork from Human Demonstrations
23. NeurIPS 2026AdaptFlow: State-Anchored Goal Conditioning with Flow Matching for Offline Goal-Conditioned RL
24. NeurIPS 2026Adaptive and Neutral Theory of Evolution Strategies for Large Language Models
25. NeurIPS 2026Adaptive Communication Range for Scalable Cooperative Multi-Agent Reinforcement Learning
26. NeurIPS 2026Adaptive Inference for Functionals of M-Estimands
27. NeurIPS 2026Adaptive Scheduling Pipeline For Multi-Instance Asynchronous Reinforcement Learning
28. NeurIPS 2026Adaptive Stepsizes for Eligibility Traces in Deep Reinforcement Learning
29. NeurIPS 2026Addressing Exogenous Variability in Cooperative Multi-Agent Reinforcement Learning
30. NeurIPS 2026Addressing Sparse-Rewards in RL with Scalable Hierarchical Novel Eigen Options
31. NeurIPS 2026Adversary-Robust Learning from Fully Asynchronous Directional Derivative Estimates
32. NeurIPS 2026AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning
33. NeurIPS 2026AETDICE: Unified Framework and Offline Optimization for Nonlinear Multi-Objective RL
34. NeurIPS 2026AffectGPT-RL: Revealing Roles of Reinforcement Learning in Open-Vocabulary Emotion Recognition
35. NeurIPS 2026AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems
36. NeurIPS 2026Agentic Reward Modeling: Verifying GUI Agent via Progressive Trajectory-Grounded Interaction
37. NeurIPS 2026Aligning Flow Map Policies with Optimal $Q$-Guidance
38. NeurIPS 2026Alignment Dynamics in LLM Fine-Tuning
39. NeurIPS 2026AlphaPareto: Formulaic Alpha Discovery with LLM-Guided Multi-Objective Reinforcement Learning
40. NeurIPS 2026Amortized Molecular Optimization via Group Relative Policy Optimization
41. NeurIPS 2026An Analytical Model of Compute-limited Multistage Training Pipelines
42. NeurIPS 2026Angular Networks: Low-Bit Learning from Randomized Similarity Estimators
43. NeurIPS 2026ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Scheduling
44. NeurIPS 2026ASTOR: Multi-Task Code Reinforcement Learning via Utility-Driven Coordination
45. NeurIPS 2026AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs
46. NeurIPS 2026Attention-Based Soft Answer Sets
47. NeurIPS 2026Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs
48. NeurIPS 2026AURA: An Autonomous Retouching Agent with Photographic Visual Thinking
49. NeurIPS 2026Axiomatic Reinforcement Learning for Open Multi-Agent Systems from Shapley Axioms
50. NeurIPS 2026Axiomatic World Modeling for Physics 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。