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 2,985 篇，第 60 / 60 页

2951. NeurIPS 2026Video Models Can Reason with Verifiable Rewards
2952. NeurIPS 2026Video-FLAIR: Not Whether to Reason, But How
2953. NeurIPS 2026VidHalluDoctor: Learning Video Differences to Mitigate Hallucinations in Vision-Language Models
2954. NeurIPS 2026VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning
2955. NeurIPS 2026VISD: Enhancing Video Reasoning via Structured Self-Distillation
2956. NeurIPS 2026VisionCreator-R1: A Reflection-Enhanced Native Visual-Generation Agentic Model
2957. NeurIPS 2026VisionCreator-S1: Evolving Visual-Generation Agents via Skill-GRPO Optimization
2958. NeurIPS 2026Visual Grounding First, Multimodal In-context Learning Follows
2959. NeurIPS 2026Visual Robustness and Neural Alignment in a Shared Foraging Task: The Mouse vs. AI Benchmark
2960. NeurIPS 2026Visual-ERM: Reward Modeling for Visual Equivalence
2961. NeurIPS 2026VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learning
2962. NeurIPS 2026VSPO: Vector-Steered Policy Optimization for Controllable Model Behavior
2963. NeurIPS 2026Wasserstein residuals: Learning Gradient Flows from Population Dynamics
2964. NeurIPS 2026Wayfinder: Adaptive Resource Routing from Agent Citations
2965. NeurIPS 2026What Makes Two States the Same? Value-Aware State Matching for Multi-Turn Agent Credit Assignment
2966. NeurIPS 2026What MLLMs Learn about When they Learn about Multimodal Reasoning
2967. NeurIPS 2026When Are Compositional Problems Learnable from Verifiable Rewards?
2968. NeurIPS 2026When Do Learned State Representations Break Sensitivity Analysis?
2969. NeurIPS 2026When Does Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning
2970. NeurIPS 2026When Does Non-Uniform Replay Matter in Reinforcement Learning?
2971. NeurIPS 2026When Does Sequential Detection Collapse to a Scalar? A Necessary and Sufficient Characterisation
2972. NeurIPS 2026When Must AI Training Stage Checkpoints? A Distributional Model of Durability Boundaries at Scale
2973. NeurIPS 2026When Policies Cannot Be Retrained: A Unified Closed-Form View of Post-Training Steering in Offline Reinforcement Learning
2974. NeurIPS 2026Where Do Long Captions Fail? Position-Aware Diagnosis and Reinforcement Learning for Detailed Image Captioning
2975. NeurIPS 2026Who Should Evolve? Uncertainty-Aware Role Bottleneck Inference for Multi-Agent LLM Training
2976. NeurIPS 2026Why Copy Others? Insights into Social Learning from Multi-Agent Reinforcement Learning
2977. NeurIPS 2026Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression
2978. NeurIPS 2026Winning the Symmetry Lottery: Learning Invariance from Data Augmentations with Transformers
2979. NeurIPS 2026WorldPrism: 3D Consistency for Video World Models via Bidirectional Cross-Space Verification
2980. NeurIPS 2026WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation
2981. NeurIPS 2026WTF?! Simulation-Free Reinforcement Learning with Wasserstein-Tilted Flow Maps
2982. NeurIPS 2026Your Hypergradient is Skewed: Antithetic Neumann Estimation for Bilevel Optimization
2983. NeurIPS 2026Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor’s Internal States
2984. NeurIPS 2026Zero-Shot Instruction Following in RL via Structured LTL Representations
2985. NeurIPS 2026Zero-Violation Regret for Cooperative Markov Games with Coupled Instantaneous Hard Constraints

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。