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 911 篇，第 12 / 19 页
- ICLR 2026Policy Likelihood-based Query Sampling and Critic-Exploited Reset for Efficient Preference-based Reinforcement Learning
- ICLR 2026Policy Newton Algorithm in Reproducing Kernel Hilbert Space
- ICLR 2026PolicyFlow: Policy Optimization with Continuous Normalizing Flow in Reinforcement Learning
- ICLR 2026Polychromic Objectives for Reinforcement Learning
- ICLR 2026Pose-RFT: Aligning MLLMs for 3D Pose Generation via Hybrid Action Reinforcement Fine-Tuning
- ICLR 2026Post-training Large Language Models for Diverse High-Quality Responses
- ICLR 2026PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework
- ICLR 2026Potentially Optimal Joint Actions Recognition for Cooperative Multi-Agent Reinforcement Learning
- ICLR 2026Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs
- ICLR 2026Predicting LLM Output Length via Entropy-Guided Representations
- ICLR 2026Predictive CVaR Q-learning
- ICLR 2026Preference-based Policy Optimization from Sparse-reward Offline Dataset
- ICLR 2026PreferThinker: Reasoning-based Personalized Image Preference Assessment
- ICLR 2026Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentations
- ICLR 2026Pretrain Value, Not Reward: Decoupled Value Policy Optimization
- ICLR 2026Primal-Dual Policy Optimization for Adversarial Linear CMDPs
- ICLR 2026Principled Fast and Meta Knowledge Learners for Continual Reinforcement Learning
- ICLR 2026Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective
- ICLR 2026PrismAudio: Decomposed Chain-of-Thought and Multi-dimensional Rewards for Video-to-Audio Generation
- ICLR 2026PRO-MOF: Policy Optimization with Universal Atomistic Models for Controllable MOF Generation
- ICLR 2026Probing in the Dark: State Entropy Maximization for POMDPs
- ICLR 2026Probing to Refine: Reinforcement Distillation of LLM Reasoners via Explanatory Inversion
- ICLR 2026Process-Verified Reinforcement Learning for Theorem Proving via Lean
- ICLR 2026Prompt Curriculum Learning for Efficient LLM Post-Training
- ICLR 2026Prompt-MII: Meta-Learning Instruction Induction for LLMs
- ICLR 2026ProofOptimizer: Training Language Models to Simplify Proofs without Human Demonstrations
- ICLR 2026PROS: Towards Compute-Efficient RLVR via Rollout Prefix Reuse
- ICLR 2026Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?
- ICLR 2026Proximal Supervised Fine-Tuning
- ICLR 2026ProxyThinker: Test-Time Guidance through Small Visual Reasoners
- ICLR 2026PSP: Prompt-Guided Self-Training Sampling Policy for Active Prompt Learning
- ICLR 2026Q-Learning with Adjoint Matching
- ICLR 2026Q-Learning with Fine-Grained Gap-Dependent Regret
- ICLR 2026Q-learning with Posterior Sampling
- ICLR 2026Q-RAG: Long Context Multi‑Step Retrieval via Value‑Based Embedder Training
- ICLR 2026QeRL: Beyond Efficiency - Quantization-enhanced Reinforcement Learning for LLMs
- ICLR 2026QuadGPT: Native Quadrilateral Mesh Generation with Autoregressive Models
- ICLR 2026Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead
- ICLR 2026Quantile Advantage Estimation for Entropy-Safe Reasoning
- ICLR 2026QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation
- ICLR 2026QuRL: Low-Precision Reinforcement Learning for Efficient Reasoning
- ICLR 2026QuRL: Rubrics As Judge For Open-Ended Question Answering
- ICLR 2026R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?
- ICLR 2026R-Zero: Self-Evolving Reasoning LLM from Zero Data
- ICLR 2026R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learning
- ICLR 2026R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning
- ICLR 2026R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation
- ICLR 2026R2PS: Worst-Case Robust Real-Time Pursuit Strategies under Partial Observability
- ICLR 2026R4: Nested Reasoning-Retrieval for Reward Modeling in Role-Playing Agents
- ICLR 2026Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards
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。