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 49 / 60 页
- NeurIPS 2026Distribution Corrected Decision Transformer for Offline Reinforcement Learning with Imbalanced Datasets
- NeurIPS 2026Distribution-Adaptive Policy Optimization
- NeurIPS 2026Distributionally Robust Black Box Optimization-based Bidding Strategy in Auction-based Federated Learning
- NeurIPS 2026Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling
- NeurIPS 2026Distributionally Robust Token Optimization in RLHF
- NeurIPS 2026Distributionally-Robust Policy Learning from Observational Data
- NeurIPS 2026DiversePlace: Diversity-Seeking Curriculum Reinforcement Learning for Macro Placement
- NeurIPS 2026DocAtlas: Long-Document Understanding as Mutable-State Interaction
- NeurIPS 2026Dodge-It: Learning Collision-Aware VLA Models for Robotic Manipulation
- NeurIPS 2026Don’t Let Gains FADE: Breaking Down Policy Gradient Weights in RL
- NeurIPS 2026DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training
- NeurIPS 2026Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems
- NeurIPS 2026Drift Q-Learning
- NeurIPS 2026Drifting Field Policy: Wasserstein Gradient Flow on Policy Space for Offline-to-Online RL
- NeurIPS 2026DRILL: Training World Models to Improve Policies, Not Predict Pixels
- NeurIPS 2026DRTriton: Large-Scale Synthetic Data Driven Reinforcement Learning for Triton Kernel Generation
- NeurIPS 2026DualKV: Shared-Prompt Flash Attention for Efficient RL Training with Large Rollouts and Long Contexts
- NeurIPS 2026DUDS: Dual-stage Data Selection for Efficient Reinforcement Learning with Verifiable Rewards
- NeurIPS 2026Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of Uncertainty
- NeurIPS 2026DynamAuction: a reinforcement learning environment for repeated auction with dynamic value
- NeurIPS 2026Dynamic Tokenization via Reinforcement Patching: End-to-end Training and Zero-shot Transfer
- NeurIPS 2026Dynamic Treatment on Networks
- NeurIPS 2026Dynamics-Informed Adaptive Offline RL for Real-Time Tokamak Plasma Control
- NeurIPS 2026Early Prediction of Future Behavioral Strategy from Process Traces
- NeurIPS 2026ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learning
- NeurIPS 2026Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing
- NeurIPS 2026Effectiveness of Curriculum Learning Depends on Reward Sparsity and Competing Optima
- NeurIPS 2026Efficient Diffusion Policy Fine Tuning with Latent Noise Representation Bridging
- NeurIPS 2026Efficient Gradient-Aware Asynchronous Reinforcement Learning for LLM Post-Training
- NeurIPS 2026Efficient Off-Policy RL for Video Generation via Forward-Consistent Reward Matching
- NeurIPS 2026Efficient Test-Time Adaptation For Robot Policies
- NeurIPS 2026EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts
- NeurIPS 2026Enhancing Speech Large Language Models through Reinforced Behavior Alignment
- NeurIPS 2026Entropy Dynamics of Agent Reinforcement Learning
- NeurIPS 2026Equivariant Reinforcement Learning for Clifford Quantum Circuit Synthesis
- NeurIPS 2026Error-Guided Bellman Calibration for Semi-Offline Value Estimation
- NeurIPS 2026Escaping Path Mirages in Offline Goal-Conditioned Reinforcement Learning
- NeurIPS 2026ESSAM: A Novel Competitive Evolution Strategies Approach to Reinforcement Learning for Memory Efficient LLMs Fine-Tuning
- NeurIPS 2026EventLens: Event-Structure Reinforcement Learning for Video Understanding
- NeurIPS 2026EvoGround: Self-Evolving Video Agents for Video Temporal Grounding
- NeurIPS 2026Evolutionary System Prompt Learning for Reinforcement Learning in LLMs
- NeurIPS 2026EvoMM: Reinforced Self-Evolving Multimodal Agentic Memory
- NeurIPS 2026EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling
- NeurIPS 2026Expanding LLM Agent Boundaries with Strategy-Guided Exploration
- NeurIPS 2026Explaining and Preventing Alignment Collapse in Iterative RLHF
- NeurIPS 2026ExpLang: Improved Exploration and Exploitation in LLM Reasoning with On-Policy Thinking Language Selection
- NeurIPS 2026Exploration as Constrained Policy-Space Optimization
- NeurIPS 2026Exploration via Exploitation: The Blessing of Reward Diversity in Personalized Federated RL
- NeurIPS 2026Exploring Lifelong Adaptation: In-Context Reinforcement Learning in Non-Stationary Environments
- NeurIPS 2026Exploring Starts Are Not Enough: Counterexamples and a Fix for Monte Carlo Exploring Starts
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。