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 1,827 篇，第 26 / 37 页
- ICLR 2025Taming Overconfidence in LLMs: Reward Calibration in RLHF
- ICLR 2025Temporal Difference Learning: Why It Can Be Fast and How It Will Be Faster
- ICLR 2025The "Law'' of the Unconscious Contrastive Learner: Probabilistic Alignment of Unpaired Modalities
- ICLR 2025The Value of Sensory Information to a Robot
- ICLR 2025ToolGen: Unified Tool Retrieval and Calling via Generation
- ICLR 2025TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning
- ICLR 2025Toward Efficient Multi-Agent Exploration With Trajectory Entropy Maximization
- ICLR 2025Toward Exploratory Inverse Constraint Inference with Generative Diffusion Verifiers
- ICLR 2025Towards Empowerment Gain through Causal Structure Learning in Model-Based Reinforcement Learning
- ICLR 2025Towards Federated RLHF with Aggregated Client Preference for LLMs
- ICLR 2025Towards General-Purpose Model-Free Reinforcement Learning
- ICLR 2025Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations
- ICLR 2025Towards Improving Exploration through Sibling Augmented GFlowNets
- ICLR 2025TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees
- ICLR 2025Tractable Multi-Agent Reinforcement Learning through Behavioral Economics
- ICLR 2025Training Language Models to Self-Correct via Reinforcement Learning
- ICLR 2025Training Large Language Models for Retrieval-Augmented Question Answering through Backtracking Correction
- ICLR 2025Trajectory-Class-Aware Multi-Agent Reinforcement Learning
- ICLR 2025Transformer-Squared: Self-adaptive LLMs
- ICLR 2025Transformers Can Learn Temporal Difference Methods for In-Context Reinforcement Learning
- ICLR 2025Uncertainty and Influence aware Reward Model Refinement for Reinforcement Learning from Human Feedback
- ICLR 2025Understanding Constraint Inference in Safety-Critical Inverse Reinforcement Learning
- ICLR 2025Unhackable Temporal Reward for Scalable Video MLLMs
- ICLR 2025UniCO: On Unified Combinatorial Optimization via Problem Reduction to Matrix-Encoded General TSP
- ICLR 2025Unsupervised Zero-Shot Reinforcement Learning via Dual-Value Forward-Backward Representation
- ICLR 2025UTILITY: Utilizing Explainable Reinforcement Learning to Improve Reinforcement Learning
- ICLR 2025Value-aligned Behavior Cloning for Offline Reinforcement Learning via Bi-level Optimization
- ICLR 2025Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF
- ICLR 2025VICtoR: Learning Hierarchical Vision-Instruction Correlation Rewards for Long-horizon Manipulation
- ICLR 2025VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning
- ICLR 2025VTDexManip: A Dataset and Benchmark for Visual-tactile Pretraining and Dexterous Manipulation with Reinforcement Learning
- ICLR 2025VVC-Gym: A Fixed-Wing UAV Reinforcement Learning Environment for Multi-Goal Long-Horizon Problems
- ICLR 2025WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning
- ICLR 2025What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis
- ICLR 2025What Makes a Good Diffusion Planner for Decision Making?
- ICLR 2025WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct
- ICLR 2025XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning
- ICLR 2025Zero-shot Model-based Reinforcement Learning using Large Language Models
- ICLR 2025Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models
- ICLR 2025Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference
- ICLR 2024$\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis
- ICLR 2024$\pi$2vec: Policy Representation with Successor Features
- ICLR 2024A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
- ICLR 2024A Dynamical View of the Question of Why
- ICLR 2024A Newborn Embodied Turing Test for Comparing Object Segmentation Across Animals and Machines
- ICLR 2024A Policy Gradient Method for Confounded POMDPs
- ICLR 2024Achieving Fairness in Multi-Agent MDP Using Reinforcement Learning
- ICLR 2024Achieving Sample and Computational Efficient Reinforcement Learning by Action Space Reduction via Grouping
- ICLR 2024Active Retrosynthetic Planning Aware of Route Quality
- ICLR 2024Adaptive Rational Activations to Boost Deep Reinforcement Learning
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。