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 55 / 60 页
- NeurIPS 2026PhysTacGen: Physics-Aware Visual-Tactile Sensor Image Generation
- NeurIPS 2026PiCA: Pivot-Based Credit Assignment For Search Agentic Reinforcement Learning
- NeurIPS 2026Plan2Sense: Open-World Task Planning in Epistemic States via Interleaved Ontic and Sensing Actions
- NeurIPS 2026PLATO: Pointer Learner for Agent and Task Openness
- NeurIPS 2026Plausible Biomolecular Structure Prediction via Physics-informed Reinforcement Learning
- NeurIPS 2026PO-PDDL: Learning Symbolic POMDPs from Visual Demonstrations for Robot Planning Under Uncertainty
- NeurIPS 2026PoEM: Predicting New RL Outcomes from Existing Policies
- NeurIPS 2026Policy Gradient Algorithms in Average-Reward Multichain MDPs
- NeurIPS 2026Policy-DRIFT: Dynamic Reward-Informed Flow Trajectory Steering
- NeurIPS 2026Policy-Level Exploration for Coordinated Multi-Agent Reinforcement Learning
- NeurIPS 2026Posterior Sampling-based Online Learning for Episodic POMDPs
- NeurIPS 2026Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation
- NeurIPS 2026PRECISE: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models
- NeurIPS 2026Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization
- NeurIPS 2026PreFT: Prefill-only finetuning for inference efficiency
- NeurIPS 2026Preserving Exploration for LLM Reasoning via Mean Order-Statistic Alignment
- NeurIPS 2026Prevailing Bisimulation Metric Learning Is Biased: Implicit Regularization and Its Remedy
- NeurIPS 2026PriFT: Prior-Support Guided Token Reweighting for Supervised Fine-Tuning
- NeurIPS 2026Principled Policy Optimization for LLMs via Self-Normalized Importance Sampling
- NeurIPS 2026ProgramBench: Can Language Models Rebuild Programs From Scratch?
- NeurIPS 2026Programmatic Reasoning with Structural Schema: A Unified Framework for Multi-Table Inference
- NeurIPS 2026Proportionality in Ranking Compression
- NeurIPS 2026Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction–Reality Gaps
- NeurIPS 2026Provably Safe, Yet Performant Reinforcement Learning
- NeurIPS 2026Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization
- NeurIPS 2026Q-MMR: Off-Policy Evaluation via Recursive Reweighting and Moment Matching
- NeurIPS 2026Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing
- NeurIPS 2026QMaxCal: Path-Space Regularization for Open Quantum Control via Girsanov's Theorem
- NeurIPS 2026Quantile Geometry Regularization for Distributional Reinforcement Learning
- NeurIPS 2026Quantile-Coupled Flow Matching for Distributional Reinforcement Learning
- NeurIPS 2026Quest: Training Frontier Deep Research Agents with Fully Synthetic Tasks
- NeurIPS 2026Quotient-Categorical Representations for Bellman-Compatible Average-Reward Distributional Reinforcement Learning
- NeurIPS 2026RAHF: Reward-Amplified Human Feedback for Closed-Loop Policy Fine-Tuning
- NeurIPS 2026Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding
- NeurIPS 2026Read It Back: Pretrained MLLMs Are Zero-shot Reward Models for Text-to-Image Generation
- NeurIPS 2026Reason to Play: Behavioral and Brain Alignment Between Frontier LRMs and Human Game Learners
- NeurIPS 2026Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck
- NeurIPS 2026Reasoning Warm-up: Scaling Label-free RL via Verifiable Surrogate Rewards
- NeurIPS 2026Reasoning with Sampling: Cutting at Decision Points
- NeurIPS 2026RECAP: Looking Once Is Not Enough for Vision-Language Reasoning
- NeurIPS 2026ReCon: Toward Balanced Learning under Inter-Context and Context-Memory Conflicts
- NeurIPS 2026Reconciling Operational Energy Trilemma: A Heterogeneous Risk-Constrained MDP Framework with Residual Policy Learning
- NeurIPS 2026Reconciling Safety and Performance via Dual-Expert Offline Imitation Learning
- NeurIPS 2026Rectified Policy Rollouts with Hierarchical Expert Guidance for Neural Combinatorial Optimization
- NeurIPS 2026ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving
- NeurIPS 2026Reflective Prompted Policy Optimization: Trajectory-Grounded Revision and Salience Bias
- NeurIPS 2026ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation
- NeurIPS 2026Reinforcement Learning Agents Are Swimmers
- NeurIPS 2026Reinforcement learning enhanced flow matching for reference-based tumor generation on unpaired CT images
- NeurIPS 2026Reinforcement Learning for Code Optimization
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。