强化学习论文趋势 2023–2026

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。

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 1,640 篇，第 7 / 33 页

301. ICLR 2025Noise-conditioned Energy-based Annealed Rewards (NEAR): A Generative Framework for Imitation Learning from Observation
302. ICLR 2025Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching
303. ICLR 2025Null Counterfactual Factor Interactions for Goal-Conditioned Reinforcement Learning
304. ICLR 2025OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models
305. ICLR 2025ODE-based Smoothing Neural Network for Reinforcement Learning Tasks
306. ICLR 2025Offline Hierarchical Reinforcement Learning via Inverse Optimization
307. ICLR 2025Offline RL in Regular Decision Processes: Sample Efficiency via Language Metrics
308. ICLR 2025Offline RL with Smooth OOD Generalization in Convex Hull and its Neighborhood
309. ICLR 2025OGBench: Benchmarking Offline Goal-Conditioned RL
310. ICLR 2025OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code
311. ICLR 2025On a Connection Between Imitation Learning and RLHF
312. ICLR 2025On Generalization Across Environments In Multi-Objective Reinforcement Learning
313. ICLR 2025On Minimizing Adversarial Counterfactual Error in Adversarial Reinforcement Learning
314. ICLR 2025On Rollouts in Model-Based Reinforcement Learning
315. ICLR 2025On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback
316. ICLR 2025On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations
317. ICLR 2025On the Modeling Capabilities of Large Language Models for Sequential Decision Making
318. ICLR 2025On-the-fly Preference Alignment via Principle-Guided Decoding
319. ICLR 2025Online Preference Alignment for Language Models via Count-based Exploration
320. ICLR 2025Online Reinforcement Learning in Non-Stationary Context-Driven Environments
321. ICLR 2025Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein Regularization
322. ICLR 2025Online-to-Offline RL for Agent Alignment
323. ICLR 2025Open-World Reinforcement Learning over Long Short-Term Imagination
324. ICLR 2025Optimal Non-Asymptotic Rates of Value Iteration for Average-Reward Markov Decision Processes
325. ICLR 2025Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimization
326. ICLR 2025Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization
327. ICLR 2025OptionZero: Planning with Learned Options
328. ICLR 2025ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization
329. ICLR 2025Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Control
330. ICLR 2025OvercookedV2: Rethinking Overcooked for Zero-Shot Coordination
331. ICLR 2025PABBO: Preferential Amortized Black-Box Optimization
332. ICLR 2025Pareto Prompt Optimization
333. ICLR 2025PEAR: Primitive Enabled Adaptive Relabeling for Boosting Hierarchical Reinforcement Learning
334. ICLR 2025PersonalLLM: Tailoring LLMs to Individual Preferences
335. ICLR 2025PN-GAIL: Leveraging Non-optimal Information from Imperfect Demonstrations
336. ICLR 2025POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding
337. ICLR 2025Policy Optimization under Imperfect Human Interactions with Agent-Gated Shared Autonomy
338. ICLR 2025PolyNet: Learning Diverse Solution Strategies for Neural Combinatorial Optimization
339. ICLR 2025Post-hoc Reward Calibration: A Case Study on Length Bias
340. ICLR 2025Preference Elicitation for Offline Reinforcement Learning
341. ICLR 2025Preference Optimization for Reasoning with Pseudo Feedback
342. ICLR 2025Prevalence of Negative Transfer in Continual Reinforcement Learning: Analyses and a Simple Baseline
343. ICLR 2025Prioritized Generative Replay
344. ICLR 2025Procedural Synthesis of Synthesizable Molecules
345. ICLR 2025Process Reward Model with Q-value Rankings
346. ICLR 2025PWM: Policy Learning with Multi-Task World Models
347. ICLR 2025Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation
348. ICLR 2025Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning
349. ICLR 2025QMP: Q-switch Mixture of Policies for Multi-Task Behavior Sharing
350. ICLR 2025RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization

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。