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 784 篇，第 7 / 16 页
- NeurIPS 2025Incentivizing LLMs to Self-Verify Their Answers
- NeurIPS 2025Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models
- NeurIPS 2025Incremental Sequence Classification with Temporal Consistency
- NeurIPS 2025Information-Theoretic Reward Decomposition for Generalizable RLHF
- NeurIPS 2025Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning
- NeurIPS 2025InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
- NeurIPS 2025Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Regularized Exploration in Reinforcement Learning
- NeurIPS 2025Intrinsic Goals for Autonomous Agents: Model-Based Exploration in Virtual Zebrafish Predicts Ethological Behavior and Whole-Brain Dynamics
- NeurIPS 2025Inverse Optimization Latent Variable Models for Learning Costs Applied to Route Problems
- NeurIPS 2025IOSTOM: Offline Imitation Learning from Observations via State Transition Occupancy Matching
- NeurIPS 2025Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs
- NeurIPS 2025Iterative Foundation Model Fine-Tuning on Multiple Rewards
- NeurIPS 2025Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning
- NeurIPS 2025Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning
- NeurIPS 2025KeeA*: Epistemic Exploratory A* Search via Knowledge Calibration
- NeurIPS 2025Kernel conditional tests from learning-theoretic bounds
- NeurIPS 2025Kinaema: a recurrent sequence model for memory and pose in motion
- NeurIPS 2025KL Penalty Control via Perturbation for Direct Preference Optimization
- NeurIPS 2025KL-Regularized RLHF with Multiple Reference Models: Exact Solutions and Sample Complexity
- NeurIPS 2025Knot So Simple: A Minimalistic Environment for Spatial Reasoning
- NeurIPS 2025Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering
- NeurIPS 2025KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation
- NeurIPS 2025KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning
- NeurIPS 2025KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills
- NeurIPS 2025LaRes: Evolutionary Reinforcement Learning with LLM-based Adaptive Reward Search
- NeurIPS 2025Large Language Models as End-to-end Combinatorial Optimization Solvers
- NeurIPS 2025Large language models can learn and generalize steganographic chain-of-thought under process supervision
- NeurIPS 2025Latent Chain-of-Thought for Visual Reasoning
- NeurIPS 2025Latent Mixture of Symmetries for Sample-Efficient Dynamic Learning
- NeurIPS 2025LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers
- NeurIPS 2025Learning and Planning Multi-Agent Tasks via an MoE-based World Model
- NeurIPS 2025Learning Dense Hand Contact Estimation from Imbalanced Data
- NeurIPS 2025Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning
- NeurIPS 2025Learning from A Single Markovian Trajectory: Optimality and Variance Reduction
- NeurIPS 2025Learning from Demonstrations via Capability-Aware Goal Sampling
- NeurIPS 2025Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models
- NeurIPS 2025Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization
- NeurIPS 2025Learning in Stackelberg Mean Field Games: A Non-Asymptotic Analysis
- NeurIPS 2025Learning Interactive World Model for Object-Centric Reinforcement Learning
- NeurIPS 2025Learning Interestingness in Automated Mathematical Theory Formation
- NeurIPS 2025Learning Intractable Multimodal Policies with Reparameterization and Diversity Regularization
- NeurIPS 2025Learning Memory-Enhanced Improvement Heuristics for Flexible Job Shop Scheduling
- NeurIPS 2025Learning Parameterized Skills from Demonstrations
- NeurIPS 2025Learning Personalized Ad Impact via Contextual Reinforcement Learning under Delayed Rewards
- NeurIPS 2025Learning Preferences without Interaction for Cooperative AI: A Hybrid Offline-Online Approach
- NeurIPS 2025Learning to Better Search with Language Models via Guided Reinforced Self-Training
- NeurIPS 2025Learning to Clean: Reinforcement Learning for Noisy Label Correction
- NeurIPS 2025Learning to Control Free-Form Soft Swimmers
- NeurIPS 2025Learning to Plan Like the Human Brain via Visuospatial Perception and Semantic-Episodic Synergistic Decision-Making
- NeurIPS 2025Learning to Reason under Off-Policy Guidance
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。