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 760 篇，第 8 / 16 页

351. NeurIPS 2026Learning to Bid in Repeated Second-Price Auctions with Dynamic Values and Aggregated Feedback
352. NeurIPS 2026Learning to Cut: Reinforcement Learning for Benders Decomposition
353. NeurIPS 2026Learning to Explore with Parameter-Space Noise: A Deep Dive into Parameter-Space Noise for Reinforcement Learning with Verifiable Rewards
354. NeurIPS 2026Learning to Follow In-Context Watermark Instructions via Self-Distillation
355. NeurIPS 2026Learning to Group and Order: Cross-Instance Self-Supervised RL for Vision-Centric MLLMs
356. NeurIPS 2026Learning to Learn from Multimodal Experience
357. NeurIPS 2026Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs
358. NeurIPS 2026Learning to Surpass: Training Tool-Using Agents with Anchored Feedback
359. NeurIPS 2026Learning to Trigger: Reinforcement Learning at the Large Hadron Collider
360. NeurIPS 2026Learning to Undo: Transfer Reinforcement Learning under State Space Transformations
361. NeurIPS 2026Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift
362. NeurIPS 2026Learning When to Think: Adaptive Internal Computation for Reinforcement Learning
363. NeurIPS 2026Leveraging Dale’s Principle as an Inductive Bias in Recurrent Neural Networks
364. NeurIPS 2026Leveraging Latent Visual Reasoning in Silence
365. NeurIPS 2026Leveraging Psychophysical Attentional Distribution for Gaze-Augmented Reward Modeling
366. NeurIPS 2026LiFT: Likelihood-Free Tree-Structured Policy Optimization for Flow-Based VLAs
367. NeurIPS 2026Likelihood-Free Generative Policy Optimization
368. NeurIPS 2026LiveOption: Evaluating LLM Agents in Structured Option Trading with Nonlinear Payoffs
369. NeurIPS 2026LLMs as MDP Designers: A Dependency-Aware Agentic Framework for Automated Robot Policy Generation
370. NeurIPS 2026Local Policy Manifolds for Efficient Multi-Objective Reinforcement Learning
371. NeurIPS 2026Localized Dynamics-Aware Domain Adaption for Off-Dynamics Offline Reinforcement Learning
372. NeurIPS 2026LOCU: Löwdin-Orthogonalized Constraint Updates for Multi-Constraint Policy Optimization
373. NeurIPS 2026LogT: Logically Think with Images for Visual Search
374. NeurIPS 2026Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities
375. NeurIPS 2026Look Before You Reason: Implicit Visual Thinking for Efficient Multimodal Reasoning
376. NeurIPS 2026LookThere! Sparse Vision by Reinforced Selection
377. NeurIPS 2026Loop-Free Inverse Reinforcement Learning via Sequential Value Recovery
378. NeurIPS 2026LoopRPT: Reinforcement Pre-Training for Looped Language Models
379. NeurIPS 2026Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning
380. NeurIPS 2026LucidNFT: LR-Anchored Multi-Reward Preference Optimization for Flow-Based Real-World Super-Resolution
381. NeurIPS 2026Lyapunov-Driven Optimistic Learning for Online Scheduling with Multi-Stage Tasks
382. NeurIPS 2026Managing Self-Learning Experts under Per-Round Budget Constraints
383. NeurIPS 2026Manifold-weighted neural networks
384. NeurIPS 2026MaPP: A Unified Marginalized Posterior-Predictive Framework for Data-Efficient RLVR
385. NeurIPS 2026MASTARS: Multi-Agent Sequential Trajectory Augmentation with Return-Conditioned Subgoals
386. NeurIPS 2026MaxIM: Maximally Informative Incremental Summarization via Reinforcement Learning
387. NeurIPS 2026Mean-Field Control on Sparse Graphs: From Local Limits to GNNs via Neighborhood Distributions
388. NeurIPS 2026Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition
389. NeurIPS 2026Measuring and Strengthening Behavioral Suppression in Language Models
390. NeurIPS 2026Measuring Coherence in Predictive Models
391. NeurIPS 2026MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments
392. NeurIPS 2026Medical LLMs as Medical World Models: Unified Policy-Dynamics Learning with Test-Time Search
393. NeurIPS 2026MedIGen: Reliable Medical Illustration Generation via Interleaved Introspective Reasoning
394. NeurIPS 2026MedVIGOR: Visual Evidence Internalization for Observation-Driven Reasoning in Medical VLMs
395. NeurIPS 2026Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
396. NeurIPS 2026Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents
397. NeurIPS 2026Meta-Learning Preferences for Multilingual LLM Alignment
398. NeurIPS 2026Meta-Reinforcement Learning with Zero-Shot Reinforcement Learning
399. NeurIPS 2026Meta-TTRL: A Metacognitive Framework for Self-Improving Test-Time Reinforcement Learning for T2I Generation in Unified Multimodal Models
400. NeurIPS 2026Mind the Gap: Information Disadvantage as a Learning Signal in Cooperative MARL

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。