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 53 / 60 页
- NeurIPS 2026LookThere! Sparse Vision by Reinforced Selection
- NeurIPS 2026Loop-Free Inverse Reinforcement Learning via Sequential Value Recovery
- NeurIPS 2026LoopRPT: Reinforcement Pre-Training for Looped Language Models
- NeurIPS 2026Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning
- NeurIPS 2026LucidNFT: LR-Anchored Multi-Reward Preference Optimization for Flow-Based Real-World Super-Resolution
- NeurIPS 2026Lyapunov-Driven Optimistic Learning for Online Scheduling with Multi-Stage Tasks
- NeurIPS 2026Managing Self-Learning Experts under Per-Round Budget Constraints
- NeurIPS 2026Manifold-weighted neural networks
- NeurIPS 2026MaPP: A Unified Marginalized Posterior-Predictive Framework for Data-Efficient RLVR
- NeurIPS 2026MASTARS: Multi-Agent Sequential Trajectory Augmentation with Return-Conditioned Subgoals
- NeurIPS 2026MaxIM: Maximally Informative Incremental Summarization via Reinforcement Learning
- NeurIPS 2026Mean-Field Control on Sparse Graphs: From Local Limits to GNNs via Neighborhood Distributions
- NeurIPS 2026Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition
- NeurIPS 2026Measuring and Strengthening Behavioral Suppression in Language Models
- NeurIPS 2026Measuring Coherence in Predictive Models
- NeurIPS 2026MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments
- NeurIPS 2026Medical LLMs as Medical World Models: Unified Policy-Dynamics Learning with Test-Time Search
- NeurIPS 2026MedIGen: Reliable Medical Illustration Generation via Interleaved Introspective Reasoning
- NeurIPS 2026MedVIGOR: Visual Evidence Internalization for Observation-Driven Reasoning in Medical VLMs
- NeurIPS 2026Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
- NeurIPS 2026Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents
- NeurIPS 2026Meta-Learning Preferences for Multilingual LLM Alignment
- NeurIPS 2026Meta-Reinforcement Learning with Zero-Shot Reinforcement Learning
- NeurIPS 2026Meta-TTRL: A Metacognitive Framework for Self-Improving Test-Time Reinforcement Learning for T2I Generation in Unified Multimodal Models
- NeurIPS 2026Mind the Gap: Information Disadvantage as a Learning Signal in Cooperative MARL
- NeurIPS 2026MIRA: Reinforcing Multimodal Reasoning via Deceptive Contextual Augmentation
- NeurIPS 2026Mitigating Compounding Errors in Online Reinforcement Learning via Optimal Transport Regularized Flow Matching
- NeurIPS 2026Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization
- NeurIPS 2026Mitigating Overgeneralization in RND via Spectral Target Design
- NeurIPS 2026Mitigating Retaliatory Algorithmic Collusion in Repeated Games
- NeurIPS 2026Mitigating Reward Hacking via Task Representations
- NeurIPS 2026Model-based Bootstrap of Controlled Markov Chains
- NeurIPS 2026Modeling quantum neural network gradient with reinforcement learning
- NeurIPS 2026Modelling Opinion Dynamics at Scale with Deep MARL
- NeurIPS 2026MOSAIC: Scaling Long-Horizon Language Agents via Multi-Scale Adaptive Inference Control
- NeurIPS 2026MPQ: A Message-Passing View of Post-Training Quantization
- NeurIPS 2026Mult-DPO: Multinomial Direct Preference Optimization for Recommender Systems
- NeurIPS 2026Multi-Objective Reinforcement Learning Using Routed Ensembles and Trajectory Attribution
- NeurIPS 2026Multi-Stage Planning from Single-Stage Data: Reinforcement Learning Helps Composition but Requires Anchoring
- NeurIPS 2026Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards
- NeurIPS 2026Multi-Turn RL Makes Small Language Model Competitive for Optimization Modeling
- NeurIPS 2026NASDAQ: Normalized Observation Space Dynamics-Augmented Q-Learning
- NeurIPS 2026Nearly Optimal Fixed-Confidence Best-Arm Identification with 1-Bit Feedback
- NeurIPS 2026Need-Aware Multi-Objective Reinforcement Learning for Emotionally Intelligent LLM Agents
- NeurIPS 2026Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
- NeurIPS 2026Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
- NeurIPS 2026NestRL: A Nested Training Regime for Mutual Adaptation in Human–AI Teaming
- NeurIPS 2026Neural Chameleons: Language Models Can Learn to Hide Their Thoughts from Unseen Activation Monitors
- NeurIPS 2026Neural Garbage Collection: Learning to Forget while Learning to Reason
- NeurIPS 2026Neural Modal Decomposition: Architectural Priors from Observables
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。