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 2,079 篇，第 11 / 42 页

501. ICML 2026Learning Unmasking Policies for Diffusion Language Models
502. ICML 2026Learning What to Generate: A Reinforcement Learning-based Closed-Loop Augmentation Framework for Person Re-identification
503. ICML 2026Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use
504. ICML 2026Learning-To-Measure: In-Context Active Feature Acquisition
505. ICML 2026LECTOR: Joint Learning of Scientific Reasoning Graphs and Introduction Generation
506. ICML 2026Leveraging Machine Unlearning for Cost-Efficient Preference Alignment
507. ICML 2026LightningRL: Breaking the Accuracy–Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning
508. ICML 2026LIMMT: Less Is More for Motion Tracking
509. ICML 2026Linguistic Relative Policy Optimization for Video Anomaly Reasoning
510. ICML 2026LithoGRPO: Fast Inverse Lithography via GRPO Reinforced Flow Matching
511. ICML 2026LLM-Guided Communication for Cooperative Multi-Agent Reinforcement Learning
512. ICML 2026LLM4Cov: Execution-Aware Agentic Learning for High-coverage Testbench Generation
513. ICML 2026Local Policies for Graph-Structured Markov Decision Processes
514. ICML 2026Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization
515. ICML 2026Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism
516. ICML 2026Long-term Fairness with Selective Labels
517. ICML 2026Lookahead Unmasking Elicits Reliable Decoding in Diffusion Language Models
518. ICML 2026LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation
519. ICML 2026MAFE: Enabling Equitable Algorithm Design in Multi-Agent Multi-Stage Decision-Making Systems
520. ICML 2026MAGIC: A Co-Evolving Attacker–Defender Adversarial Game for Robust LLM Safety
521. ICML 2026ManiSoft: Towards Vision-Language Manipulation for Soft Continuum Robotics
522. ICML 2026MARS-SQL: A Multi-Agent Reinforcement Learning Framework For Text-To-SQL
523. ICML 2026MASH: Modeling Abstention via Selective Help-Seeking
524. ICML 2026MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference
525. ICML 2026Maximum Likelihood Reinforcement Learning
526. ICML 2026MCCE: A Framework for Multi-LLM Collaborative Search in Discrete Spaces with Similarity-Filtered Preference Learning
527. ICML 2026MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning
528. ICML 2026Mean Flow Policy Optimization
529. ICML 2026MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding
530. ICML 2026Med-Scout: Curing MLLMs' Geometric Blindness in Medical Perception via Geometry-Aware RL Post-Training
531. ICML 2026Meerkat-VL: Implicit Risk Safety Alignment in Multimodal LLMs via Perceptual Reasoning and Self-Verification
532. ICML 2026Mem-T: Densifying Rewards for Long-Horizon Memory Agents
533. ICML 2026MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning
534. ICML 2026MET-Bench: Multimodal Entity Tracking for Evaluating the Limitations of Vision-Language and Reasoning Models
535. ICML 2026Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization
536. ICML 2026Milestone-Guided Policy Learning for Long-Horizon Language Agents
537. ICML 2026Mind Dreamer: Untethering Imagination via Active Causal Intervention on Latent Manifolds
538. ICML 2026Mind the Budget: Accelerating Deep Reinforcement Learning using Constrained Early Exit Neural Networks
539. ICML 2026Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL
540. ICML 2026MindZero: Learning Online Mental Reasoning With Zero Annotations
541. ICML 2026MiniMax Learning of Interpretable Factored Stochastic Policies from Conjoint Data, with Uncertainty Quantification
542. ICML 2026Minimax Optimal Strategy for Delayed Observations in Online Reinforcement Learning
543. ICML 2026Minimax-Optimal Policy Regret in Partially Observable Markov Games
544. ICML 2026Mirror Descent Actor Critic via Bounded Advantage Learning
545. ICML 2026Mitigating Plasticity Loss through Architectural Design in Continual Learning
546. ICML 2026Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling
547. ICML 2026ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering
548. ICML 2026MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baseline
549. ICML 2026MMKU-Bench: A Multimodal Update Benchmark for Diverse Visual Knowledge
550. ICML 2026Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity Analysis

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。