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 6,885 篇，第 14 / 138 页
- ICLR 2026Improving Discrete Diffusion Unmasking Policies Beyond Explicit Reference Policies
- ICLR 2026Improving Feasibility via Fast Autoencoder-Based Projections
- ICLR 2026Improving Human-AI Coordination through Online Adversarial Training and Generative Models
- ICLR 2026Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimization
- ICLR 2026In-Context Compositional Q-Learning for Offline Reinforcement Learning
- ICLR 2026In-Context Learning for Pure Exploration
- ICLR 2026In-The-Flow Agentic System Optimization for Effective Planning and Tool Use
- ICLR 2026Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning
- ICLR 2026Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards
- ICLR 2026Incentivizing LLM Reasoning via Reinforcement Learning with Functional Monte Carlo Tree Search
- ICLR 2026Inference-time scaling of diffusion models through classical search
- ICLR 2026InfGen: Scenario Generation as Next Token Group Prediction
- ICLR 2026Influence without Confounding: Causal Discovery from Temporal Data with Long-term Carry-over Effects
- ICLR 2026Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn LLM Agents
- ICLR 2026Information-based Value Iteration Networks for Decision Making Under Uncertainty
- ICLR 2026InfoScan: Information-Efficient Visual Scanning via Resource-Adaptive Walks
- ICLR 2026Inpainting-Guided Policy Optimization for Diffusion Large Language Models
- ICLR 2026InputDSA: Demixing, then comparing recurrent and externally driven dynamics
- ICLR 2026InSight-o3: Empowering Multimodal Foundation Models with Generalized Visual Search
- ICLR 2026Instance-Dependent Fixed-Budget Pure Exploration in Reinforcement Learning
- ICLR 2026Instance-wise Adaptive Scheduling via Derivative-Free Meta-Learning
- ICLR 2026Intention-Conditioned Flow Occupancy Models
- ICLR 2026Inter-Agent Relative Representations for Multi-Agent Option Discovery
- ICLR 2026Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrieval
- ICLR 2026Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment
- ICLR 2026Invert4TVG: A Temporal Video Grounding Framework with Inversion Tasks Preserving Action Understanding Ability
- ICLR 2026Is Pure Exploitation Sufficient in Exogenous MDPs with Linear Function Approximation?
- ICLR 2026IterResearch: Rethinking Long-Horizon Agents via Markovian State Reconstruction
- ICLR 2026J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning
- ICLR 2026Jackpot: Align Actor-Policy Distribution for scalable and stable RL for LLM
- ICLR 2026Judo: A Juxtaposed Domain-oriented Multimodal Reasoner for Industrial Anomaly QA
- ICLR 2026Kevin: Multi-Turn RL for Generating CUDA Kernels
- ICLR 2026Kimi-Dev: Agentless Training as Skill Prior for SWE-agents
- ICLR 2026KL-Regularized Reinforcement Learning is Designed to Mode Collapse
- ICLR 2026Koopman-Assisted Trajectory Synthesis: A Data Augmentation Framework for Offline Imitation Learning
- ICLR 2026LadderSym: A Multimodal Interleaved Transformer for Music Practice Error Detection
- ICLR 2026Language Agents for Hypothesis-driven Clinical Decision Making with Reinforcement Learning
- ICLR 2026LaSeR: Reinforcement Learning with Last-Token Self-Rewarding
- ICLR 2026Latent Adaptation of Foundation Policies for Sim-to-Real Transfer
- ICLR 2026Latent Visual Reasoning
- ICLR 2026Learn More with Less: Uncertainty Consistency Guided Query Selection for RLVR
- ICLR 2026Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning
- ICLR 2026Learn to Reason Efficiently with Adaptive Length-based Reward Shaping
- ICLR 2026LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models
- ICLR 2026Learning Correlated Reward Models: Statistical Barriers and Opportunities
- ICLR 2026Learning Dynamics Feature Representation via Policy Attention for Dynamic Path Planning in Urban Road Networks
- ICLR 2026Learning Efficient and Interpretable Multi-Agent Communication
- ICLR 2026Learning from Algorithm Feedback: One-Shot SAT Solver Guidance with GNNs
- ICLR 2026Learning from Synthetic Data Improves Multi-hop Reasoning
- ICLR 2026Learning Massively Multitask World Models for Continuous Control
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。