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 2,079 篇，第 13 / 42 页
- ICML 2026Online Compatible Reward Identification from Preference Feedback
- ICML 2026Online Robust Reinforcement Learning with General Function Approximation
- ICML 2026Online Rubrics Elicitation from Pairwise Comparisons
- ICML 2026Open Materials Generation with Inference-Time Reinforcement Learning
- ICML 2026Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence
- ICML 2026Ophiuchus: Incentivizing Tool-augmented ''Think with Images'' for Joint Medical Segmentation, Understanding and Reasoning
- ICML 2026Opt-Miner: Empowering Information-Seeking Agent with Tree-Guided Data Synthesis for Optimization Modeling
- ICML 2026Optimal Regret for Policy Optimization in Contextual Bandits
- ICML 2026Optimal Transport for LLM Reward Modeling from Noisy Feedback
- ICML 2026Optimizing Agentic Reasoning with Retrieval via Synthetic Semantic Information Gain Reward
- ICML 2026Optimizing Visual Generative Models via Distribution-wise Rewards
- ICML 2026Orchestrating Spatial Semantics via a Zone-Graph Paradigm for Intricate Indoor Scene Generation
- ICML 2026ORLoopBench: Solver-in-the-Loop Benchmarks for Self-Correction and Behavioral Rationality in Operations Research
- ICML 2026Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning
- ICML 2026PAC-Bayesian Reinforcement Learning Trains Generalizable Policies
- ICML 2026PACE: Parameter Change for Unsupervised Environment Design
- ICML 2026PADD: Path-Aligned Decompression Distillation for Non-Router Teacher to Guide MoE Student Learning
- ICML 2026PAMD: Structured Adaptive Distances for Bisimulation Representations in Visual Reinforcement Learning
- ICML 2026Partial Identification of Policy Values under Network Interference
- ICML 2026Particles Don’t Care About Z: Towards Scaling Entropy Estimation of Unnormalized Densities
- ICML 2026Path-Coupled Bellman Flows for Distributional Reinforcement Learning
- ICML 2026Path-dependent Discrete Amortized Inference
- ICML 2026PAWS: Preference Learning with Advantage-Weighted Segments
- ICML 2026Perceptual Flow Network for Visually Grounded Reasoning
- ICML 2026Performative Policy Gradient: Optimality in Performative Reinforcement Learning
- ICML 2026Pessimistic Verification for Open-Ended Math Questions
- ICML 2026Phase-Aware Mixture of Experts for Agentic Reinforcement Learning
- ICML 2026PISCES: Annotation-free Text-to-Video Post-Training via Optimal Transport-Aligned Rewards
- ICML 2026PLaID++: A Preference Aligned Language Model for Targeted Inorganic Materials Design
- ICML 2026Plan in Sandbox, Navigate in Open Worlds: Learning Physics-Grounded Abstracted Experience for Embodied Navigation
- ICML 2026Plan Then Action: High-Level Planning Guidance Reinforcement Learning for LLM Reasoning
- ICML 2026Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control
- ICML 2026PMSPO: Progressive Matching and Semantic-Aware Policy Optimization for Camouflaged Object Detection
- ICML 2026POLIA: Policy Optimization with Visual-Object-Level Intrinsic Advantage for Multimodal Reasoning
- ICML 2026Policy Search via Bayesian Optimization with Temporal Difference Gaussian Processes
- ICML 2026Policy-Driven World Model Adaptation for Robust Offline Model-based Reinforcement Learning
- ICML 2026PolicyGuard: Towards Test-time and Step-level Adversary Defense for Reinforcement Learning Agent
- ICML 2026PoMtVRS: Preference-Optimized Multi-Task Vehicle Routing Solver with Preference Gating
- ICML 2026Population-Free Pareto Tracking for Sample-Efficient Multi-Policy MORL
- ICML 2026PortraitRL: Reinforcement Learning for Personalized Portrait Pose Transfer with Multi-Objective Reward Modeling
- ICML 2026Positive–Unlabeled Reinforcement Learning Distillation for On-Premise Small Models
- ICML 2026Post-Training Language Models for Crosslingual Consistency
- ICML 2026PosterAgent: Agentic Poster Generation via Stage-Aware Reinforcement Learning
- ICML 2026Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning
- ICML 2026Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces
- ICML 2026PowerFlow: Unlocking the Dual Nature of LLMs via Principled Distribution Matching
- ICML 2026Preference-Enhanced Reinforcement Learning for Pluralistic Image Inpainting
- ICML 2026Preserving Plasticity in Continual Learning via Dynamical Isometry
- ICML 2026PretrainZero: Reinforcement Active Learning on Pretraining Data
- ICML 2026Principled RL for Flow Matching Emerges from the Chunk-level Policy Optimization
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。