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 6,885 篇，第 77 / 138 页
- ICML 2025Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner
- ICML 2025Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks
- ICML 2025Teaching Language Models to Critique via Reinforcement Learning
- ICML 2025Temporal Difference Flows
- ICML 2025Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning
- ICML 2025Test-Time Adaptation for Online Vision-Language Navigation with Feedback-based Reinforcement Learning
- ICML 2025Test-Time Adaptation with Binary Feedback
- ICML 2025Test-time Adapted Reinforcement Learning with Action Entropy Regularization
- ICML 2025TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization
- ICML 2025The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning
- ICML 2025The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking
- ICML 2025The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks
- ICML 2025The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes
- ICML 2025The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
- ICML 2025The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability
- ICML 2025The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data
- ICML 2025Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization
- ICML 2025Think Twice, Act Once: A Co-Evolution Framework of LLM and RL for Large-Scale Decision Making
- ICML 2025Time-Aware World Model for Adaptive Prediction and Control
- ICML 2025Towards Cost-Effective Reward Guided Text Generation
- ICML 2025Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning
- ICML 2025Towards Theoretical Understanding of Sequential Decision Making with Preference Feedback
- ICML 2025Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings
- ICML 2025Training Flexible Models of Genetic Variant Effects from Functional Annotations using Accelerated Linear Algebra
- ICML 2025Transfer Q-Learning with Composite MDP Structures
- ICML 2025Trust-Region Twisted Policy Improvement
- ICML 2025TtBA: Two-third Bridge Approach for Decision-Based Adversarial Attack
- ICML 2025Universal Approximation Theorem of Deep Q-Networks
- ICML 2025Unraveling the Interplay between Carryover Effects and Reward Autocorrelations in Switchback Experiments
- ICML 2025Unveiling Markov heads in Pretrained Language Models for Offline Reinforcement Learning
- ICML 2025Value-Based Deep RL Scales Predictably
- ICML 2025Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach
- ICML 2025VinePPO: Refining Credit Assignment in RL Training of LLMs
- ICML 2025Vintix: Action Model via In-Context Reinforcement Learning
- ICML 2025Wait-Less Offline Tuning and Re-solving for Online Decision Making
- ICML 2025Wasserstein Policy Optimization
- ICML 2025When Maximum Entropy Misleads Policy Optimization
- ICML 2025When to retrain a machine learning model
- ICML 2025Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning
- ICML 2025Zero Shot Generalization of Vision-Based RL Without Data Augmentation
- ICML 2025Zero-Shot Offline Imitation Learning via Optimal Transport
- NeurIPS 2025$\texttt{G1}$: Teaching LLMs to Reason on Graphs with Reinforcement Learning
- NeurIPS 2025$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training
- NeurIPS 20251000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities
- NeurIPS 2025A Bayesian Fast-Slow Framework to Mitigate Interference in Non-Stationary Reinforcement Learning
- NeurIPS 2025A Clean Slate for Offline Reinforcement Learning
- NeurIPS 2025A Closer Look to Positive-Unlabeled Learning from Fine-grained Perspectives: An Empirical Study
- NeurIPS 2025A Differential and Pointwise Control Approach to Reinforcement Learning
- NeurIPS 2025A Finite Sample Analysis of Distributional TD Learning with Linear Function Approximation
- NeurIPS 2025A Generalized Bisimulation Metric of State Similarity between Markov Decision Processes: From Theoretical Propositions to Applications
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。