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 24 / 138 页
- ICLR 2026UrbanVerse: Scaling Urban Simulation by Watching City-Tour Videos
- ICLR 2026Use the Online Network If You Can: Towards Fast and Stable Reinforcement Learning
- ICLR 2026Using Reinforcement Learning to Train Large Language Models to Explain Human Decisions
- ICLR 2026Value Flows
- ICLR 2026Value Gradient Flow: Behavior-Regularized RL without Regularization
- ICLR 2026Value Matching: Scalable and Gradient-Free Reward-Guided Flow Adaptation
- ICLR 2026Variance-Dependent Regret Lower Bounds for Contextual Bandits
- ICLR 2026Variational Reasoning for Language Models
- ICLR 2026VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models
- ICLR 2026VeriRole: Verifiable Role-Awareness through Hint-Guided Reinforcement Learning
- ICLR 2026VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Tasks
- ICLR 2026Video-KTR: Reinforcing Video Reasoning via Key Token Attribution
- ICLR 2026Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools
- ICLR 2026VideoZoomer: Reinforcement-Learned Temporal Focusing for Long Video Reasoning
- ICLR 2026ViPER: Empowering the Self-Evolution of Visual Perception Abilities in Vision-Language Models
- ICLR 2026Virne: A Comprehensive Benchmark for RL-based Network Resource Allocation in NFV
- ICLR 2026Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
- ICLR 2026Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play
- ICLR 2026VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning
- ICLR 2026Visual Jigsaw Post-Training Improves MLLMs
- ICLR 2026Visual Planning: Let's Think Only with Images
- ICLR 2026VITA: Zero-Shot Value Functions via Test-Time Adaptation of Vision–Language Models
- ICLR 2026VowelPrompt: Hearing Speech Emotions from Text via Vowel-level Prosodic Augmentation
- ICLR 2026VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use
- ICLR 2026WARC-Bench: Web Archive based Benchmark for GUI Subtask Executions
- ICLR 2026Wavelet Predictive Representations for Non-Stationary Reinforcement Learning
- ICLR 2026wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models
- ICLR 2026We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning
- ICLR 2026WebArbiter: A Generative Reasoning Process Reward Model for Web Agents
- ICLR 2026WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents
- ICLR 2026WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning
- ICLR 2026WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning
- ICLR 2026Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels
- ICLR 2026WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflection
- ICLR 2026WebWatcher: Breaking New Frontiers of Vision-Language Deep Research Agent
- ICLR 2026What Generative Search Engines Like and How to Optimize Web Content Cooperatively
- ICLR 2026What Matters for Batch Online Reinforcement Learning in Robotics?
- ICLR 2026Whatever Remains Must Be True: Filtering Drives Reasoning in LLMs, Shaping Diversity
- ICLR 2026When a Robot is More Capable than a Human: Learning from Constrained Demonstrators
- ICLR 2026When Data is the Algorithm: A Systematic Study and Curation of Preference Optimization Datasets
- ICLR 2026When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training
- ICLR 2026When Is Diversity Rewarded in Cooperative Multi-Agent Learning?
- ICLR 2026When More is Less: Understanding Chain-of-Thought Length in LLMs
- ICLR 2026When Silence Is Golden: Can LLMs Learn to Abstain in Temporal QA and Beyond?
- ICLR 2026Who Matters Matters: Agent-Specific Conservative Offline MARL
- ICLR 2026WholeBodyVLA: Towards Unified Latent VLA for Whole-body Loco-manipulation Control
- ICLR 2026Why DPO is a Misspecified Estimator and How to Fix It
- ICLR 2026Wiki-R1: Incentivizing Multimodal Reasoning for Knowledge-based VQA via Data and Sampling Curriculum
- ICLR 2026WIMLE: Uncertainty‑Aware World Models with IMLE for Sample‑Efficient Continuous Control
- ICLR 2026WMPO: World Model-based Policy Optimization for Vision-Language-Action Models
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。