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 26 / 42 页
- ICML 2025NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations
- ICML 2025Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback
- ICML 2025Near-Optimal Sample Complexity for MDPs via Anchoring
- ICML 2025Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning
- ICML 2025Neurosymbolic World Models for Sequential Decision Making
- ICML 2025Novelty Detection in Reinforcement Learning with World Models
- ICML 2025O-MAPL: Offline Multi-agent Preference Learning
- ICML 2025Of Mice and Machines: A Comparison of Learning Between Real World Mice and RL Agents
- ICML 2025Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation
- ICML 2025Off-Policy Evaluation under Nonignorable Missing Data
- ICML 2025Offline Opponent Modeling with Truncated Q-driven Instant Policy Refinement
- ICML 2025Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation
- ICML 2025Omni-Angle Assault: An Invisible and Powerful Physical Adversarial Attack on Face Recognition
- ICML 2025On Teacher Hacking in Language Model Distillation
- ICML 2025On the Adversarial Robustness of Multi-Kernel Clustering
- ICML 2025On the Guidance of Flow Matching
- ICML 2025On the Robustness of Reward Models for Language Model Alignment
- ICML 2025Online Episodic Convex Reinforcement Learning
- ICML 2025Online Laplacian-Based Representation Learning in Reinforcement Learning
- ICML 2025Online Learning in Risk Sensitive constrained MDP
- ICML 2025Online Pre-Training for Offline-to-Online Reinforcement Learning
- ICML 2025Online Robust Reinforcement Learning Through Monte-Carlo Planning
- ICML 2025Optimizing Language Models for Inference Time Objectives using Reinforcement Learning
- ICML 2025Optimizing Test-Time Compute via Meta Reinforcement Finetuning
- ICML 2025Outsourced Diffusion Sampling: Efficient Posterior Inference in Latent Spaces of Generative Models
- ICML 2025Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization
- ICML 2025Partially Observable Reinforcement Learning with Memory Traces
- ICML 2025Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data
- ICML 2025Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning
- ICML 2025PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning
- ICML 2025PILAF: Optimal Human Preference Sampling for Reward Modeling
- ICML 2025PIPA: Preference Alignment as Prior-Informed Statistical Estimation
- ICML 2025Policy Filtration for RLHF to Mitigate Noise in Reward Models
- ICML 2025Policy Gradient with Tree Expansion
- ICML 2025Policy Guided Tree Search for Enhanced LLM Reasoning
- ICML 2025Policy Optimization for CMDPs with Bandit Feedback: Learning Stochastic and Adversarial Constraints
- ICML 2025Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning
- ICML 2025Policy-labeled Preference Learning: Is Preference Enough for RLHF?
- ICML 2025Policy-Regret Minimization in Markov Games with Function Approximation
- ICML 2025Polynomial-Time Approximability of Constrained Reinforcement Learning
- ICML 2025Position: Constants are Critical in Regret Bounds for Reinforcement Learning
- ICML 2025Position: General Intelligence Requires Reward-based Pretraining
- ICML 2025Position: Iterative Online-Offline Joint Optimization is Needed to Manage Complex LLM Copyright Risks
- ICML 2025Position: Lifetime tuning is incompatible with continual reinforcement learning
- ICML 2025Position: LLMs Need a Bayesian Meta-Reasoning Framework for More Robust and Generalizable Reasoning
- ICML 2025Position: We Need An Algorithmic Understanding of Generative AI
- ICML 2025Power Mean Estimation in Stochastic Continuous Monte-Carlo Tree Search
- ICML 2025Preference Adaptive and Sequential Text-to-Image Generation
- ICML 2025Preference Controllable Reinforcement Learning with Advanced Multi-Objective Optimization
- ICML 2025Preference Optimization for Combinatorial Optimization Problems
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。