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 2,494 篇，第 7 / 50 页

301. NeurIPS 2026Incentivizing Medical Vision Capabilities from Large-Scale Multimodal Pre-training
302. NeurIPS 2026Independent Learning of Nash Equilibria in Partially Observable Markov Potential Games with Decoupled Dynamics
303. NeurIPS 2026Inferring learning rules in deep neural network architectures from animal learning data
304. NeurIPS 2026Information Templates: A New Paradigm for Intelligent Active Feature Acquisition
305. NeurIPS 2026Informed Posterior Sampling: More Efficient Online Learning with Few Offline Demonstrations in Average-Reward MDPs
306. NeurIPS 2026Instability of Meta-Learning Intrinsic Rewards for Policy Gradient Reinforcement Learning
307. NeurIPS 2026Intent Factored Generation: Unleashing the Diversity in Your Language Model
308. NeurIPS 2026Interactive Combinatorial Reinforcement Learning for Knowledge Graph Reasoning
309. NeurIPS 2026Interleaved Latent Thinking and Adaptive Termination for Efficient Reasoning LLMs
310. NeurIPS 2026Intra-Option Fitted Q-Evaluation: Evaluating Hierarchical Policies from Non-Hierarchical Data
311. NeurIPS 2026Inverse Linear Bandits via Linear Programs
312. NeurIPS 2026Irreducible Supervision Enables Compositional Generalization in Post-Training
313. NeurIPS 2026Is Backpropagation Optimal? When Synthetic Gradients Improve Sample Efficiency
314. NeurIPS 2026It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs
315. NeurIPS 2026Iterative Gumbel Planning for Continuous Control
316. NeurIPS 2026Iterative Latent Refinement for Value Learning in Offline Goal-Conditioned RL
317. NeurIPS 2026Joint Optimization of Tool Creation and Use for Large Language Model Agents
318. NeurIPS 2026Jointly Reinforcing Diversity and Quality in Language Model Generations
319. NeurIPS 2026Jump Start Your Policy Learning with Lessons from 145,000 Training Runs
320. NeurIPS 2026KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards
321. NeurIPS 2026Kernel Value Regression in Offline Reinforcement Learning
322. NeurIPS 2026KNN Implementation Details Can Dramatically Change Performance: An Example from Cover Trees
323. NeurIPS 2026Know Your Task, Learn It Right: Task-Aware Optimistic Value Learning for Multi-Task Multi-Agent Reinforcement Learning
324. NeurIPS 2026Knowing When to Ask: Segment-Level Credit Assignment for LLM Tool Use
325. NeurIPS 2026kVNN: Learnable Volterra Network Kernels
326. NeurIPS 2026LADDERS: Length-Aware Data Distribution and Existing-Response Speculation for Fast RL Rollout Generation
327. NeurIPS 2026LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving
328. NeurIPS 2026Latency-Conditioned Selection Bias in RLHF
329. NeurIPS 2026Latent Reasoning in Continuous Space for Unified Multimodal Models
330. NeurIPS 2026LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models
331. NeurIPS 2026Learning Better Certified Models from Empirically-Robust Teachers
332. NeurIPS 2026Learning Chance-Constrained MDPs with Bellman Distributional Certificates
333. NeurIPS 2026Learning CLI Agents with Structured Action Credit under Selective Observation
334. NeurIPS 2026Learning Collision‑Free Dispatch Policies for Route‑Wise Decision‑Dependent Anomaly Detection
335. NeurIPS 2026Learning Contextual Causal Dynamics for Robust Exploration in Reinforcement Learning
336. NeurIPS 2026Learning Cost-Efficient Autoscaling for Latency-Constrained Disaggregated LLM Serving
337. NeurIPS 2026Learning Distributions from Multiple Data Providers
338. NeurIPS 2026Learning From Failures: Efficient Reinforcement Learning Control with Episodic Memory
339. NeurIPS 2026Learning from Language Feedback via Variational Policy Distillation
340. NeurIPS 2026Learning Generalizable Hand-Object Tracking Control without Human Demonstrations
341. NeurIPS 2026Learning in Causal Markov Games
342. NeurIPS 2026Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with Transformers
343. NeurIPS 2026Learning Large-Scale Competitive Team Behaviors with Mean-Field Interactions
344. NeurIPS 2026Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport
345. NeurIPS 2026Learning Neuronal Wiring Rules from Morphological Token Sequences
346. NeurIPS 2026Learning Planning Budgets in Real-Time RL
347. NeurIPS 2026Learning Process Rewards via Visitation Matching for Efficient RL
348. NeurIPS 2026Learning Reusable Motor Motifs for Continuous Animal Behavior Modeling
349. NeurIPS 2026Learning Robust Reasoning through Guided Adversarial Self-Play
350. NeurIPS 2026Learning to Audit ML Models with Theory of Mind

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。