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 51 / 60 页
- NeurIPS 2026Grouped Adaptive Head Mixing for Personalized Multi-Task Federated Reinforcement Learning
- NeurIPS 2026Hadamard Representation: Scaffolding Performance Across Model-free RL
- NeurIPS 2026Hearing the Unspoken: Simulator-Induced Asymmetric-View Policy Optimization for Proactive Task-Oriented Dialogue
- NeurIPS 2026Heterogeneous Agent Collaborative Reinforcement Learning
- NeurIPS 2026Hide to Guide: Learning via Semantic Masking
- NeurIPS 2026Hider–Seeker Self-Play: Geometry-Verifiable Process Rewards for Long-Horizon Visual Search
- NeurIPS 2026Hierarchical Concept Geometry in Language Representations Emerges from Word Co-occurrence
- NeurIPS 2026HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models
- NeurIPS 2026High-Dimensional Robotic Reinforcement Learning with Developing Synergies
- NeurIPS 2026Higher-Order Action Supervision Makes A Strong Policy Class
- NeurIPS 2026HiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video Generation
- NeurIPS 2026Hitting Time Isomorphism for Multi-Stage Planning with Foundation Policies
- NeurIPS 2026Hodge Laplacian Quasi-Harmonic Flows for Option Discovery
- NeurIPS 2026HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
- NeurIPS 2026HOPE: Hand-Object Pressure Estimation from Monocular Videos
- NeurIPS 2026Horizon Adaptive Offline Policy Learning via Value Stitching
- NeurIPS 2026How does RL Post-training Induce Skill Composition? A Case Study on Countdown
- NeurIPS 2026How Neural Reward Models Learn Features for Policy Optimization: A Single-Index Analysis
- NeurIPS 2026Hybrid-LoRA: Bridging Full Fine-Tuning and Low-Rank Adaptation for Post-Training
- NeurIPS 2026IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards
- NeurIPS 2026Imitation Dominates Reinforcement: Direct In-Context RL Is Closer to ICL Than RL
- NeurIPS 2026Imperfect World Models are Exploitable
- NeurIPS 2026Improved Regret Analysis For Parallel Gaussian Process Bandit Optimization
- NeurIPS 2026Improved Regret bounds in Tabular Reinforcement Learning under Local Differential Privacy
- NeurIPS 2026Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- NeurIPS 2026Incentivizing Medical Vision Capabilities from Large-Scale Multimodal Pre-training
- NeurIPS 2026Independent Learning of Nash Equilibria in Partially Observable Markov Potential Games with Decoupled Dynamics
- NeurIPS 2026Inferring learning rules in deep neural network architectures from animal learning data
- NeurIPS 2026Information Templates: A New Paradigm for Intelligent Active Feature Acquisition
- NeurIPS 2026Informed Posterior Sampling: More Efficient Online Learning with Few Offline Demonstrations in Average-Reward MDPs
- NeurIPS 2026Instability of Meta-Learning Intrinsic Rewards for Policy Gradient Reinforcement Learning
- NeurIPS 2026Intent Factored Generation: Unleashing the Diversity in Your Language Model
- NeurIPS 2026Interactive Combinatorial Reinforcement Learning for Knowledge Graph Reasoning
- NeurIPS 2026Interleaved Latent Thinking and Adaptive Termination for Efficient Reasoning LLMs
- NeurIPS 2026Intra-Option Fitted Q-Evaluation: Evaluating Hierarchical Policies from Non-Hierarchical Data
- NeurIPS 2026Inverse Linear Bandits via Linear Programs
- NeurIPS 2026Irreducible Supervision Enables Compositional Generalization in Post-Training
- NeurIPS 2026Is Backpropagation Optimal? When Synthetic Gradients Improve Sample Efficiency
- NeurIPS 2026It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs
- NeurIPS 2026Iterative Gumbel Planning for Continuous Control
- NeurIPS 2026Iterative Latent Refinement for Value Learning in Offline Goal-Conditioned RL
- NeurIPS 2026Joint Optimization of Tool Creation and Use for Large Language Model Agents
- NeurIPS 2026Jointly Reinforcing Diversity and Quality in Language Model Generations
- NeurIPS 2026Jump Start Your Policy Learning with Lessons from 145,000 Training Runs
- NeurIPS 2026KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards
- NeurIPS 2026Kernel Value Regression in Offline Reinforcement Learning
- NeurIPS 2026KNN Implementation Details Can Dramatically Change Performance: An Example from Cover Trees
- NeurIPS 2026Know Your Task, Learn It Right: Task-Aware Optimistic Value Learning for Multi-Task Multi-Agent Reinforcement Learning
- NeurIPS 2026Knowing When to Ask: Segment-Level Credit Assignment for LLM Tool Use
- NeurIPS 2026kVNN: Learnable Volterra Network Kernels
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。