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 485 篇，第 6 / 10 页
- CVPR 2026Talk2Move Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes
- CVPR 2026Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion
- CVPR 2026TaskForce Cooperative Multi-agent Reinforcement Learning for Multi-task Optimization
- CVPR 2026TempR1 Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement
- CVPR 2026The Image as Its Own Reward Reinforcement Learning with Adversarial
- CVPR 2026The Missing GAP From Solving Square Jigsaw Puzzles to Handling
- CVPR 2026ThinkGen Generalized Thinking for Visual Generation
- CVPR 2026Thinking with Drafts Speculative Temporal Reasoning for Efficient Long Video
- CVPR 2026Thinking with Frames Generative Video Distortion Evaluation via Frame Reward
- CVPR 2026Thinking with Programming Vision Towards a Unified View for Thinking
- CVPR 2026Thinking With Videos Multimodal Tool-Augmented Reinforcement Learning for Long Video
- CVPR 2026Thinking-while-Generating Interleaving Textual Reasoning throughout Visual Generation
- CVPR 2026TimeLens Rethinking Video Temporal Grounding with Multimodal LLMs
- CVPR 2026Token Warping Helps MLLMs Look from Nearby Viewpoints
- CVPR 2026Towards Policy-Adaptive Image Guardrail Benchmark and Method
- CVPR 2026Training High-Level Schedulers with Execution-Feedback Reinforcement Learning for Long-Horizon GUI
- CVPR 2026TSTM Temporal Segmentation for Task-relevant Mask in Visual Reinforcement Learning
- CVPR 2026TTRV Test-Time Reinforcement Learning for Vision Language Models
- CVPR 2026Tutor-Student Reinforcement Learning A Dynamic Curriculum for Robust Deepfake Detection
- CVPR 2026UIKA Fast Universal Head Avatar from Pose-Free Images
- CVPR 2026Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal
- CVPR 2026Unified Generation and Self-Verification for Vision-Language Models via Advantage Decoupled
- CVPR 2026Unified Multimodal Models as Auto-Encoders
- CVPR 2026Unified Spherical Frontend Learning Rotation-Equivariant Representations of Spherical Images from
- CVPR 2026UniGen-1.5 Enhancing Image Generation and Editing through Reward Unification in
- CVPR 2026Unique Lives Shared World Learning from Single-Life Videos
- CVPR 2026Unleashing VLA Potentials in Autonomous Driving via Explicit Learning from
- CVPR 2026Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategy
- CVPR 2026VAR RL Done Right Tackling Asynchronous Policy Conflicts in Visual
- CVPR 2026VAST Video Ability-Stratified Taxonomy for Data-Efficient Video Reasoning
- CVPR 2026VesMamba 3D Pulmonary Vessel Segmentation from CT images via Mamba
- CVPR 2026Video-as-Answer Predict and Generate Next Video Event with Joint-GRPO
- CVPR 2026VideoChat-M1 Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement
- CVPR 2026VideoSSR Video Self-Supervised Reinforcement Learning
- CVPR 2026VisionLeaf Entropy-Guided Leaf-First Reasoning for Efficient and Accurate Think-with-Image
- CVPR 2026VisPlay Self-Evolving Vision-Language Models
- CVPR 2026VisRef Visual Refocusing while Thinking Improves Test-Time Scaling in Multi-Modal
- CVPR 2026VOLD Reasoning Transfer from LLMs to Vision-Language Models via On-Policy
- CVPR 2026W2W Language-Model-Based Trajectory Prediction with Reinforcement Learning
- CVPR 2026WebGym Scaling Training Environments for Long-Horizon Visual Web Agents with
- CVPR 2026When Do Models Actually Decide Mapping the Layer-Wise Decision Timeline
- CVPR 2026Why Does RL Generalize Better Than SFT A Data-Centric Perspective
- CVPR 2026Write Where It Matters Policy-Guided Watermarks for 3D Gaussian Splatting
- CVPR 2025All-Optical Nonlinear Diffractive Deep Network for Ultrafast Image Denoising
- CVPR 2025AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos
- CVPR 2025AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward
- CVPR 2025Automated Proof of Polynomial Inequalities via Reinforcement Learning
- CVPR 2025AutoPresent: Designing Structured Visuals from Scratch
- CVPR 2025Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundaries
- CVPR 2025CarPlanner: Consistent Auto-regressive Trajectory Planning for Large-Scale Reinforcement Learning in Autonomous Driving
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。