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 76 / 138 页
- ICML 2025Revisiting Non-Acyclic GFlowNets in Discrete Environments
- ICML 2025Reward Translation via Reward Machine in Semi-Alignable MDPs
- ICML 2025Reward-free World Models for Online Imitation Learning
- ICML 2025Reward-Guided Prompt Evolving in Reinforcement Learning for LLMs
- ICML 2025Risk-Sensitive Theory of Mind: Coordinating with Agents of Unknown Bias using Cumulative Prospect Theory
- ICML 2025RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning
- ICML 2025RLTHF: Targeted Human Feedback for LLM Alignment
- ICML 2025Robot-Gated Interactive Imitation Learning with Adaptive Intervention Mechanism
- ICML 2025Robust Autonomy Emerges from Self-Play
- ICML 2025Robust Multi-Agent Reinforcement Learning with Stochastic Adversary
- ICML 2025Robust Multimodal Large Language Models Against Modality Conflict
- ICML 2025Robust Noise Attenuation via Adaptive Pooling of Transformer Outputs
- ICML 2025Robust Offline Reinforcement Learning with Linearly Structured $f$-Divergence Regularization
- ICML 2025Robust Reward Alignment via Hypothesis Space Batch Cutting
- ICML 2025RobustLight: Improving Robustness via Diffusion Reinforcement Learning for Traffic Signal Control
- ICML 2025RobustZero: Enhancing MuZero Reinforcement Learning Robustness to State Perturbations
- ICML 2025RuleAdapter: Dynamic Rules for training Safety Reward Models in RLHF
- ICML 2025Sable: a Performant, Efficient and Scalable Sequence Model for MARL
- ICML 2025Safe-EF: Error Feedback for Non-smooth Constrained Optimization
- ICML 2025Safety Certificate against Latent Variables with Partially Unidentifiable Dynamics
- ICML 2025Safety-Polarized and Prioritized Reinforcement Learning
- ICML 2025Sample Complexity of Distributionally Robust Off-Dynamics Reinforcement Learning with Online Interaction
- ICML 2025Sample-Optimal Agnostic Boosting with Unlabeled Data
- ICML 2025Sampling from Binary Quadratic Distributions via Stochastic Localization
- ICML 2025Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search
- ICML 2025Scaling Test-Time Compute Without Verification or RL is Suboptimal
- ICML 2025Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning
- ICML 2025Score as Action: Fine Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning
- ICML 2025Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal Transport
- ICML 2025Self-Supervised Transformers as Iterative Solution Improvers for Constraint Satisfaction
- ICML 2025SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models
- ICML 2025SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
- ICML 2025Simple Policy Optimization
- ICML 2025Sleeping Reinforcement Learning
- ICML 2025Sliding Puzzles Gym: A Scalable Benchmark for State Representation in Visual Reinforcement Learning
- ICML 2025SOLD: Slot Object-Centric Latent Dynamics Models for Relational Manipulation Learning from Pixels
- ICML 2025Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry
- ICML 2025Speeding up Policy Simulation in Supply Chain RL
- ICML 2025Square$\chi$PO: Differentially Private and Robust $\chi^2$-Preference Optimization in Offline Direct Alignment
- ICML 2025Stable Offline Value Function Learning with Bisimulation-based Representations
- ICML 2025Stay Hungry, Keep Learning: Sustainable Plasticity for Deep Reinforcement Learning
- ICML 2025Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning
- ICML 2025Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Design
- ICML 2025Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence
- ICML 2025Stochastic Encodings for Active Feature Acquisition
- ICML 2025STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving
- ICML 2025Strategic Planning: A Top-Down Approach to Option Generation
- ICML 2025Subgoal-Guided Policy Heuristic Search with Learned Subgoals
- ICML 2025Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales
- ICML 2025T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling
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。