强化学习论文趋势 2023–2026
策略优化、离线 RL 与基于环境的决策学习
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 6,885 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 484 | 233 | 297 | 56 | 1,070 |
| 2024 | 466 | 304 | 356 | 64 | 1,190 |
| 2025 | 784 | 379 | 405 | 72 | 1,640 |
| 2026 | 760 | 911 | 1,021 | 293 | 2,985 |
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 13 / 37 页
- ICLR 2026RD-HRL: Generating Reliable Sub-Goals for Long-Horizon Sparse-Reward Tasks
- ICLR 2026REA-RL: Reflection-Aware Online Reinforcement Learning for Efficient Reasoning
- ICLR 2026Real-Time Motion-Controllable Autoregressive Video Diffusion
- ICLR 2026Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment
- ICLR 2026Reasoning Boosts Opinion Alignment in LLMs
- ICLR 2026Reasoning or Retrieval? A Study of Answer Attribution on Large Reasoning Models
- ICLR 2026Reasoning with Sampling: Your Base Model is Smarter Than You Think
- ICLR 2026Reasoning-Aligned Perception Decoupling for Scalable Multi-modal Reasoning
- ICLR 2026RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Data
- ICLR 2026ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
- ICLR 2026Rectifying LLM Thought from Lens of Optimization
- ICLR 2026Recurrent Action Transformer with Memory
- ICLR 2026Reducing Belief Deviation in Reinforcement Learning for Active Reasoning
- ICLR 2026Reevaluating Policy Gradient Methods for Imperfect-Information Games
- ICLR 2026Reference Guided Skill Discovery
- ICLR 2026References Improve LLM Alignment in Non-Verifiable Domains
- ICLR 2026Refining Hybrid Genetic Search for CVRP via Reinforcement Learning-Finetuned LLM
- ICLR 2026ReFORM: Reflected Flows for On-support Offline RL via Noise Manipulation
- ICLR 2026RegionReasoner: Region-Grounded Multi-Round Visual Reasoning
- ICLR 2026Regret-Guided Search Control for Efficient Learning in AlphaZero
- ICLR 2026Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models
- ICLR 2026Reinforced Latent Reasoning for LLM-based Recommendation
- ICLR 2026Reinforcement Learning Fine-Tuning Enhances Activation Intensity and Diversity in the Internal Circuitry of LLMs
- ICLR 2026Reinforcement Learning for Machine Learning Engineering Agents
- ICLR 2026Reinforcement Learning from Dynamic Critic Feedback for Free-Form Generations
- ICLR 2026Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
- ICLR 2026Reinforcement Mid-Training
- ICLR 2026Reinforcement Unlearning via Group Relative Policy Optimization
- ICLR 2026Reinforcing Diffusion Models by Direct Group Preference Optimization
- ICLR 2026Reinforcing General Reasoning Without Verifiers
- ICLR 2026Relative Entropy Pathwise Policy Optimization
- ICLR 2026Relative Value Learning
- ICLR 2026Reliability-Adjusted Prioritized Experience Replay
- ICLR 2026Replicable Reinforcement Learning with Linear Function Approximation
- ICLR 2026Representation-Based Exploration for Language Models: From Test-Time to Post-Training
- ICLR 2026RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning
- ICLR 2026RESCHED: Rethinking Flexible Job Shop Scheduling from a Transformer-based Architecture with Simplified States
- ICLR 2026Reshaping Reasoning in LLMs: A Theoretical Analysis of RL Training Dynamics through Pattern Selection
- ICLR 2026Resisting Contextual Interference in RAG via Parametric-Knowledge Reinforcement
- ICLR 2026ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models
- ICLR 2026RESTRAIN: From Spurious Votes to Signals — Self-Training RL with Self-Penalization
- ICLR 2026Retaining Suboptimal Actions to Follow Shifting Optima in Multi-Agent Reinforcement Learning
- ICLR 2026Rethinking Policy Diversity in Ensemble Policy Gradient in Large-Scale Reinforcement Learning
- ICLR 2026ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
- ICLR 2026ReTrace: Reinforcement Learning-Guided Reconstruction Attacks on Machine Unlearning
- ICLR 2026Retro*: Optimizing LLMs for Reasoning-Intensive Document Retrieval
- ICLR 2026ReVeal: Self-Evolving Code Agents via Reliable Self-Verification
- ICLR 2026Reverse-Engineered Reasoning for Open-Ended Generation
- ICLR 2026Revisiting Group Relative Policy Optimization: Insights into On-Policy and Off-Policy Training
- ICLR 2026Revisual-R1: Advancing Multimodal Reasoning From Optimized Cold Start to Staged Reinforcement Learning
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查强化学习在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "reinforcement-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。