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 34 / 138 页
- ICML 2026Knowing When to Quit: A Principled Framework for Dynamic Abstention in LLM Reasoning
- ICML 2026Knowledge Diversion for Efficient Morphology Control and Policy Transfer
- ICML 2026LAGEA: Language Guided Embodied Agents for Robotic Manipulation
- ICML 2026Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative Policies
- ICML 2026Landmark-Guided Policy Optimization for Multi-Objective Language Model Selection
- ICML 2026Langevin Rollout Optimization for Modelic Reinforcement Learning
- ICML 2026Language-based Trial and Error Falls Behind in the Era of Experience
- ICML 2026Laplacian Representations for Decision-Time Planning
- ICML 2026LARFT: Closing the Cognition-Action Gap for Length Instruction Following in Large Language Models
- ICML 2026LASER: Learning Active Sensing for Continuum Field Reconstruction
- ICML 2026Latent Guided Sampling for Combinatorial Optimization
- ICML 2026Latent Reasoning in TRMs is Secretly a Policy Improvement Operator
- ICML 2026Latent Representation Alignment for Offline Goal-Conditioned Reinforcement Learning
- ICML 2026Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions
- ICML 2026Lavida-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models
- ICML 2026Learn from A Rationalist: Distilling Intermediate Interpretable Rationales
- ICML 2026Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs
- ICML 2026Learn to change the world: Multi-level reinforcement learning with model-changing actions
- ICML 2026Learning Anisotropic Value Geometry with Finsler Reinforcement Learning
- ICML 2026Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic
- ICML 2026Learning Disentangled Multi-Agent World Model for Decentralized Control
- ICML 2026Learning from Comparison: Constrained Projection Policy Optimization for Pareto-Front Improvement
- ICML 2026Learning Generalizable Skill Policy with Data-Efficient Unsupervised RL
- ICML 2026Learning GUI Grounding with Spatial Reasoning from Visual Feedback
- ICML 2026Learning Human-Robot Collaboration via Heterogeneous-Agent Lyapunov Policy Optimization
- ICML 2026Learning Interpretable Options by Identifying Reward Diffusion Bottlenecks in Reinforcement Learning
- ICML 2026Learning Multi-Timescale Abstractions for Hierarchical Combinatorial Planning
- ICML 2026Learning Permutation from Structure Without Supervision
- ICML 2026Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory
- ICML 2026Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning
- ICML 2026Learning Reward–Cost Balance in Safe RL via Score-Based World Models
- ICML 2026Learning Robust Multi-Agent Policies via Selective Adversarial Fault Induction
- ICML 2026Learning Self-Correction in Vision–Language Models via Rollout Augmentation
- ICML 2026Learning Structured Reasoning via Tractable Trajectory Control
- ICML 2026Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling
- ICML 2026Learning the Best Under Constraints: A Duality-Based Framework
- ICML 2026Learning the Minimum Action Distance
- ICML 2026Learning to Approximate Uniform Facility Location via Graph Neural Networks
- ICML 2026Learning to Bet for Horizon-Aware Anytime-Valid Testing
- ICML 2026Learning to Correct: Reinforcement Learning for Multi-Attempt Chain-of-Thought
- ICML 2026Learning to Decode Against Compositional Hallucination in Video Multimodal Large Language Models
- ICML 2026Learning to Discover at Test Time
- ICML 2026Learning to Evict from Key-Value Cache
- ICML 2026Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization
- ICML 2026Learning to Perceive the World Through Control: Empowerment-Based Representation Learning
- ICML 2026Learning to Rank from Incomplete Rankings
- ICML 2026Learning to Reason for Factuality
- ICML 2026Learning to Reconfigure: Configuration-Control Co-optimization of Reconfigurable Robots for Heterogeneous Locomotion
- ICML 2026Learning to Route Languages for Multilingual Policy Optimization
- ICML 2026Learning to Search and Searching to Learn for Generalization in Planning
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。