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 5 / 10 页
- CVPR 2026Reliable Clustering Number Estimation for Contrastive Multi-View Clustering
- CVPR 2026Reliable Policy Transfer for Safety-Aware End-to-End Driving with Deep Reinforcement
- CVPR 2026ReMoGen Real-time Human Interaction-to-Reaction Generation via Modular Learning from Diverse
- CVPR 2026ReMoT Reinforcement Learning with Motion Contrast Triplets
- CVPR 2026Resolving the Identity Crisis in Text-to-Image Generation
- CVPR 2026Resolving the Stability-Plasticity Dilemma in Reinforcement Learning via Complementary Continual
- CVPR 2026Rethinking 2D-3D Registration A Novel Network for High-Value Zone Selection
- CVPR 2026RetouchIQ MLLM Agents for Instruction-Based Image Retouching with Generalist Reward
- CVPR 2026REVISOR Beyond Textual Reflection Towards Multimodal Introspective Reasoning in Long-Form
- CVPR 2026Reward Sharpness-Aware Fine-Tuning for Diffusion Models
- CVPR 2026RL-ScanIQA Reinforcement-Learned Scanpaths for Blind 360deg Image Quality Assessment
- CVPR 2026RLFTSim Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning
- CVPR 2026RoboAgent Chaining Basic Capabilities for Embodied Task Planning
- CVPR 2026RoboWheel A Data Engine from Real-World Human Demonstrations for Cross-Embodiment
- CVPR 2026RunawayEvil Jailbreaking the Image-to-Video Generative Models
- CVPR 2026SafeGRPO Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization
- CVPR 2026Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement
- CVPR 2026SAMIX Reinforcing SAM2 with Semantic Adapter and Reference Selecting Policy
- CVPR 2026SAMTok Representing Any Mask with Two Words
- CVPR 2026SARL-STG A Spatially Aware Reinforcement Learning Framework for Refining MLLMs
- CVPR 2026Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs
- CVPR 2026SEBA Sample-Efficient Black-Box Attacks on Visual Reinforcement Learning
- CVPR 2026See Further Think Deeper Advancing VLMs Reasoning Ability with Low-level
- CVPR 2026See It Say It Sorted An Iterative Training-Free Framework for
- CVPR 2026Seeing is Improving Visual Feedback for Iterative Text Layout Refinement
- CVPR 2026Seeing What Matters Visual Preference Policy Optimization for Visual Generation
- CVPR 2026Seeing without Pixels Perception from Camera Trajectories
- CVPR 2026SegCompass Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning
- CVPR 2026Select Less Reason More Prioritizing Evidence Purity for Video Reasoning
- CVPR 2026SemVideo Reconstructs What You Watch from Brain Activity via Hierarchical
- CVPR 2026SenseSearch Empowering Vision-Language Models with High-Resolution Agentic Search-Reasoning via Reinforcement
- CVPR 2026ShadowDraw From Any Object to Shadow-Drawing Compositional Art
- CVPR 2026SimRecon SimReady Compositional Scene Reconstruction from Real Videos
- CVPR 2026SketchVL Policy Optimization via Fine-Grained Credit Assignment for Chart Understanding
- CVPR 2026SocialNav Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigation
- CVPR 2026SpaceTools Tool-Augmented Spatial Reasoning via Double Interactive RL
- CVPR 2026SparseCam4D Spatio-Temporally Consistent 4D Reconstruction from Sparse Cameras
- CVPR 2026Spatial-SSRL Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning
- CVPR 2026SpatialReward Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in
- CVPR 2026Specificity-aware reinforcement learning for fine-grained open-world classification
- CVPR 2026Spectrum from Defocus Fast Spectral Imaging with Chromatic Focal Stack
- CVPR 2026SpiderCam Low-Power Snapshot Depth from Differential Defocus
- CVPR 2026Splat-Based Metal Artifact Reduction in Cone-Beam CT via Compact Attenuation
- CVPR 2026SRPO Self-Referential Policy Optimization for Vision-Language-Action Models
- CVPR 2026Stable and Efficient Single-Rollout RL for Multimodal Reasoning
- CVPR 2026STAR-R1 Multi-View Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMs
- CVPR 2026Stepwise Credit Assignment for GRPO on Flow-Matching Models
- CVPR 2026Style-GRPO Semantic-Aware Preference Optimization for Image Style Transfer Guided by
- CVPR 2026StyleDoctor Towards Specialist Reward Model for Style-centric Generation Tasks
- CVPR 2026Synthetic Curriculum Reinforces Compositional Text-to-Image Generation
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。