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 405 篇，第 6 / 9 页

251. ICML 2025Online Robust Reinforcement Learning Through Monte-Carlo Planning
252. ICML 2025Optimizing Language Models for Inference Time Objectives using Reinforcement Learning
253. ICML 2025Optimizing Test-Time Compute via Meta Reinforcement Finetuning
254. ICML 2025Outsourced Diffusion Sampling: Efficient Posterior Inference in Latent Spaces of Generative Models
255. ICML 2025Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization
256. ICML 2025Partially Observable Reinforcement Learning with Memory Traces
257. ICML 2025Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data
258. ICML 2025Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning
259. ICML 2025PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning
260. ICML 2025PILAF: Optimal Human Preference Sampling for Reward Modeling
261. ICML 2025PIPA: Preference Alignment as Prior-Informed Statistical Estimation
262. ICML 2025Policy Filtration for RLHF to Mitigate Noise in Reward Models
263. ICML 2025Policy Gradient with Tree Expansion
264. ICML 2025Policy Guided Tree Search for Enhanced LLM Reasoning
265. ICML 2025Policy Optimization for CMDPs with Bandit Feedback: Learning Stochastic and Adversarial Constraints
266. ICML 2025Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning
267. ICML 2025Policy-labeled Preference Learning: Is Preference Enough for RLHF?
268. ICML 2025Policy-Regret Minimization in Markov Games with Function Approximation
269. ICML 2025Polynomial-Time Approximability of Constrained Reinforcement Learning
270. ICML 2025Position: Constants are Critical in Regret Bounds for Reinforcement Learning
271. ICML 2025Position: General Intelligence Requires Reward-based Pretraining
272. ICML 2025Position: Iterative Online-Offline Joint Optimization is Needed to Manage Complex LLM Copyright Risks
273. ICML 2025Position: Lifetime tuning is incompatible with continual reinforcement learning
274. ICML 2025Position: LLMs Need a Bayesian Meta-Reasoning Framework for More Robust and Generalizable Reasoning
275. ICML 2025Position: We Need An Algorithmic Understanding of Generative AI
276. ICML 2025Power Mean Estimation in Stochastic Continuous Monte-Carlo Tree Search
277. ICML 2025Preference Adaptive and Sequential Text-to-Image Generation
278. ICML 2025Preference Controllable Reinforcement Learning with Advanced Multi-Objective Optimization
279. ICML 2025Preference Optimization for Combinatorial Optimization Problems
280. ICML 2025Private Federated Learning using Preference-Optimized Synthetic Data
281. ICML 2025Progressively Label Enhancement for Large Language Model Alignment
282. ICML 2025Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF
283. ICML 2025Proto Successor Measure: Representing the Behavior Space of an RL Agent
284. ICML 2025Provable Maximum Entropy Manifold Exploration via Diffusion Models
285. ICML 2025Provable Policy Gradient for Robust Average-Reward MDPs Beyond Rectangularity
286. ICML 2025Provable Zero-Shot Generalization in Offline Reinforcement Learning
287. ICML 2025Provably Efficient Exploration in Inverse Constrained Reinforcement Learning
288. ICML 2025Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature Spaces
289. ICML 2025Q-Supervised Contrastive Representation: A State Decoupling Framework for Safe Offline Reinforcement Learning
290. ICML 2025QPRL : Learning Optimal Policies with Quasi-Potential Functions for Asymmetric Traversal
291. ICML 2025Quantum Algorithms for Finite-horizon Markov Decision Processes
292. ICML 2025Quantum Speedups in Regret Analysis of Infinite Horizon Average-Reward Markov Decision Processes
293. ICML 2025R*: Efficient Reward Design via Reward Structure Evolution and Parameter Alignment Optimization with Large Language Models
294. ICML 2025R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning
295. ICML 2025Random Policy Evaluation Uncovers Policies of Generative Flow Networks
296. ICML 2025Rank-One Modified Value Iteration
297. ICML 2025Reflect-then-Plan: Offline Model-Based Planning through a Doubly Bayesian Lens
298. ICML 2025Regret-Free Reinforcement Learning for Temporal Logic Specifications
299. ICML 2025Reidentify: Context-Aware Identity Generation for Contextual Multi-Agent Reinforcement Learning
300. ICML 2025ReinboT: Amplifying Robot Visual-Language Manipulation with 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。