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 54 / 60 页
- NeurIPS 2026Neural Spectral Capacity: An Architectural Quantity from Network Specification Alone
- NeurIPS 2026Neuro-Inspired Inverse Learning for Planning and Control
- NeurIPS 2026Never Stop Learning: Test-Time Reinforcement Learning for Vision-Language-Action Models
- NeurIPS 2026NitroBox: Lightning-Fast Sandbox for Large-Scale RL Training
- NeurIPS 2026Noisy Data is Destructive to Reinforcement Learning with Verifiable Rewards
- NeurIPS 2026Non-Asymptotic Best Policy Identification Guarantees in Online Reinforcement Learning
- NeurIPS 2026Not All Tokens Should Be Treated Equally: Context Credits Reassignment
- NeurIPS 2026Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR
- NeurIPS 2026NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models
- NeurIPS 2026Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders
- NeurIPS 2026Objective-Aligned Amortized Inference for Offline Bayes-Adaptive MDP Model Learning
- NeurIPS 2026Off-policy Learning with Excursion Policies
- NeurIPS 2026Offline Constrained Reinforcement Learning under Partial Data Coverage
- NeurIPS 2026Offline Inverse Reinforcement Learning with Unified Diffusion Planning
- NeurIPS 2026Offline Materials Optimization with CliqueFlowmer
- NeurIPS 2026Offline Reinforcement Learning for Plasma Control in Nuclear Fusion: Codebase and Benchmark
- NeurIPS 2026OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models
- NeurIPS 2026On the Complexity of Discounted Robust MDPs with $L_p$ Uncertainty Sets
- NeurIPS 2026On the Complexity of Offline Reinforcement Learning with Q*-Approximation and Partial Coverage
- NeurIPS 2026On the Convergence of Success Conditioning for Policy Optimization
- NeurIPS 2026On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization
- NeurIPS 2026On the Origin of Algorithmic Progress in AI: Evidence from Language Model Pre-Training
- NeurIPS 2026On-Policy Counterfactual Influence
- NeurIPS 2026One for All: A Non-Linear Transformer can enable Cross-Domain Generalization for In-Context Reinforcement Learning
- NeurIPS 2026One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective
- NeurIPS 2026Online Decision-Focused Learning under Semi-Bandit Feedback
- NeurIPS 2026OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
- NeurIPS 2026OpenSearcher: Democratizing Deep Search through a Fully Offline Pipeline with Programmatic Verification
- NeurIPS 2026OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
- NeurIPS 2026Optimistic Q-value Adaptation for Offline-to-Online Reinforcement Learning
- NeurIPS 2026Optimizer-Induced Mode Connectivity: From AdamW to Muon
- NeurIPS 2026Optimizing Agent Tool-Use via Trajectory-based Insight Evolution
- NeurIPS 2026Optimizing Social Utility in Sequential Experiments
- NeurIPS 2026Ordered Policy Optimization
- NeurIPS 2026Outbidding and Outbluffing Elite Humans: Mastering Liar’s Poker via Self-Play and Reinforcement Learning
- NeurIPS 2026Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data
- NeurIPS 2026Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
- NeurIPS 2026PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents
- NeurIPS 2026PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control
- NeurIPS 2026Parallel Computation Algorithms and Convergence Guarantees for Mean-Field Langevin Dynamics
- NeurIPS 2026Parameter Exploration for RLVR via Variational Learning
- NeurIPS 2026ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning
- NeurIPS 2026PASSAGE: A Real-Terrain Benchmark for Trustworthy Constrained Path Planning
- NeurIPS 2026PatternBloom: Empowering Agentic RAG with Externalized RL-Distilled Graph Patterns
- NeurIPS 2026Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs
- NeurIPS 2026Personalized and Collaborative Online LQR via Thompson Sampling
- NeurIPS 2026Persuasive Prediction via Decision Calibration
- NeurIPS 2026Pessimistic Latent Task-aware Optimization for Robust Offline Meta-Reinforcement Learning
- NeurIPS 2026PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning
- NeurIPS 2026PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation
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。