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 2,985 篇，第 45 / 60 页
- ICML 2026ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models
- ICML 2026Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning
- ICML 2026Well-Posed KL-Regularized Control via Wasserstein and Kalman–Wasserstein KL Divergences
- ICML 2026What Does Flow-Matching Bring to TD-Learning?
- ICML 2026What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-Zoom
- ICML 2026What Makes Value Learning Efficient in Residual Reinforcement Learning?
- ICML 2026What Reward Structure Enables Efficient Sparse-Reward RL? A Proof-of-Concept with Policy-Aware Matrix Completion
- ICML 2026What You Think is What You See: Driving Exploration in VLM Agents via Visual-Linguistic Curiosity
- ICML 2026When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPs
- ICML 2026When Does Predictive Inverse Dynamics Outperform Behavior Cloning?
- ICML 2026When RL Meets Adaptive Speculative Training: A Unified Training-Serving System
- ICML 2026When Simple Problems Wear Complex Costumes: Improving Efficiency in LRM's Adaptive Reasoning
- ICML 2026When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning
- ICML 2026Which Heads Matter for Reasoning? RL-Guided KV Cache Compression
- ICML 2026Why Dedicated Critics: Eliminating Target Drift in Multi-Constraint RL
- ICML 2026Why Linear Recurrent Memory Works in Partially Observable Reinforcement Learning
- ICML 2026Why Tree-Style Branching Matters for Thought Advantage Estimation in GRPO
- ICML 2026World Models in Pieces: Structural Certification of General Agents
- ICML 2026World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
- ICML 2026WorldCompass: Reinforcement Learning for Long-Horizon World Models
- ICML 2026WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning
- ICML 2026XRPO: Pushing the Limits of GRPO with Targeted Exploration and Exploitation
- ICML 2026You Can Learn Tokenization End-to-End with Reinforcement Learning
- ICML 2026Zero-Shot Off-Policy Learning
- ICML 2026Zero-source LLM Hallucination Detection with Human-like Criteria Probing
- NeurIPS 2026\texttt{FEROM}: Frontier Endogenous Reveal-Order Marginal Policy Optimization for Masked Diffusion LMs
- NeurIPS 2026$\gamma$-weakly $\theta$-up-concavity: A Unified Framework for Non-Convex Optimization Beyond DR-Submodular and OSS Functions
- NeurIPS 2026$\varphi$TD: Distributional Reinforcement Learning using Characteristic Functions
- NeurIPS 2026$f$-GRPO & Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment
- NeurIPS 2026$R^2E$: A Role-driven Reward Evolutionary Framework for Automated Reward Function Design
- NeurIPS 20262-Step Agent: How a Bayesian Decision Maker Learns from AI-Decision Support
- NeurIPS 2026A Computational Perspective to Data Ablation Experiments
- NeurIPS 2026A Constrained Bi-level Optimization Framework for Constrained Preference-Based Reinforcement Learning
- NeurIPS 2026A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training
- NeurIPS 2026A Geometric Perspective on Reward Function Updates in Inverse Reinforcement Learning
- NeurIPS 2026A latent control model for realistic rodent motion
- NeurIPS 2026A Model of Diverse Sampling from Language Models
- NeurIPS 2026A New Framework for Quantum Reinforcement Learning
- NeurIPS 2026A Primal-dual Approach for Semi-Infinitely Constrained Reinforcement Learning
- NeurIPS 2026A Systematic Evaluation of Co-folding Model Representations for Small-Molecule Learning
- NeurIPS 2026A$^2$IQL: Adaptive Asymmetric Implicit Q Learning for Automated Warehouse Consolidation
- NeurIPS 2026AbFlowNet: Optimizing Antibody-Antigen Binding Energy via Diffusion-GFlowNet Fusion
- NeurIPS 2026Absolute State-wise Constrained Policy Optimization: High-Probability State-wise Constraints Satisfaction
- NeurIPS 2026Accelerating Safe Reinforcement Learning with Massive Parallelism
- NeurIPS 2026ACQueReLlo: Alignment-Aware Constrained Quantization via Reinforcement Learning for Large Language Models
- NeurIPS 2026Actor-Accelerated Policy Dual Averaging for Reinforcement Learning in Continuous Action Spaces
- NeurIPS 2026Ad-Hoc Teamwork from Human Demonstrations
- NeurIPS 2026AdaptFlow: State-Anchored Goal Conditioning with Flow Matching for Offline Goal-Conditioned RL
- NeurIPS 2026Adaptive and Neutral Theory of Evolution Strategies for Large Language Models
- NeurIPS 2026Adaptive Communication Range for Scalable Cooperative Multi-Agent 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。