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 6,885 篇，第 86 / 138 页

4251. NeurIPS 2025No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes
4252. NeurIPS 2025NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation
4253. NeurIPS 2025NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation
4254. NeurIPS 2025Non-convex entropic mean-field optimization via Best Response flow
4255. NeurIPS 2025Non-rectangular Robust MDPs with Normed Uncertainty Sets
4256. NeurIPS 2025Normalizing Flows are Capable Models for Continuous Control
4257. NeurIPS 2025Novel Exploration via Orthogonality
4258. NeurIPS 2025NS-Gym: A Comprehensive and Open-Source Simulation Framework for Non-Stationary Markov Decision Processes
4259. NeurIPS 2025NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective
4260. NeurIPS 2025Off-policy Reinforcement Learning with Model-based Exploration Augmentation
4261. NeurIPS 2025Offline Actor-Critic for Average Reward MDPs
4262. NeurIPS 2025Offline Goal-conditioned Reinforcement Learning with Quasimetric Representations
4263. NeurIPS 2025Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization Strategies
4264. NeurIPS 2025Offline imitation learning in $Q^\pi$-realizable MDPs without expert realizability
4265. NeurIPS 2025Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization
4266. NeurIPS 2025OMiSO: Adaptive optimization of state-dependent brain stimulation to shape neural population states
4267. NeurIPS 2025Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
4268. NeurIPS 2025On Evaluating Policies for Robust POMDPs
4269. NeurIPS 2025On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning
4270. NeurIPS 2025On the Convergence of Single-Timescale Actor-Critic
4271. NeurIPS 2025On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization
4272. NeurIPS 2025On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning
4273. NeurIPS 2025On the Sample Complexity Bounds of Bilevel Reinforcement Learning
4274. NeurIPS 2025On the Sample Complexity of Differentially Private Policy Optimization
4275. NeurIPS 2025On-Policy Optimization with Group Equivalent Preference for Multi-Programming Language Understanding
4276. NeurIPS 2025One Subgoal at a Time: Zero-Shot Generalization to Arbitrary Linear Temporal Logic Requirements in Multi-Task Reinforcement Learning
4277. NeurIPS 2025Online Optimization for Offline Safe Reinforcement Learning
4278. NeurIPS 2025Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning
4279. NeurIPS 2025Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
4280. NeurIPS 2025Open-World Drone Active Tracking with Goal-Centered Rewards
4281. NeurIPS 2025OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles
4282. NeurIPS 2025OPHR: Mastering Volatility Trading with Multi-Agent Deep Reinforcement Learning
4283. NeurIPS 2025Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning
4284. NeurIPS 2025Optimal Regret Bounds via Low-Rank Structured Variation in Non-Stationary Reinforcement Learning
4285. NeurIPS 2025Optimal Single-Policy Sample Complexity and Transient Coverage for Average-Reward Offline RL
4286. NeurIPS 2025Optimizing Anytime Reasoning via Budget Relative Policy Optimization
4287. NeurIPS 2025Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL
4288. NeurIPS 2025Optimizing the Unknown: Black Box Bayesian Optimization with Energy-Based Model and Reinforcement Learning
4289. NeurIPS 2025Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning
4290. NeurIPS 2025OrbitZoo: Real Orbital Systems Challenges for Reinforcement Learning
4291. NeurIPS 2025ORIGAMISPACE: Benchmarking Multimodal LLMs in Multi-Step Spatial Reasoning with Mathematical Constraints
4292. NeurIPS 2025Oryx: a Scalable Sequence Model for Many-Agent Coordination in Offline MARL
4293. NeurIPS 2025OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation
4294. NeurIPS 2025Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits
4295. NeurIPS 2025OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
4296. NeurIPS 2025Pairwise Calibrated Rewards for Pluralistic Alignment
4297. NeurIPS 2025Parameter Efficient Fine-tuning via Explained Variance Adaptation
4298. NeurIPS 2025PARCO: Parallel AutoRegressive Models for Multi-Agent Combinatorial Optimization
4299. NeurIPS 2025Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)
4300. NeurIPS 2025Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems

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。