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 15 / 16 页

701. NeurIPS 2026Transfer Learning of Linear Regression with Multiple Pretrained Models: Benefiting from More Pretrained Models via Overparameterization Debiasing
702. NeurIPS 2026Treat Bias as Noise: Training Bias-Robust LLM Reasoning via Reinforcement Learning
703. NeurIPS 2026Tree Training: Efficient LLM Training on Tree-Structured Trajectories
704. NeurIPS 2026Trust Guided Decision Transformer
705. NeurIPS 2026Trust Region Q Adjoint Matching
706. NeurIPS 2026TrustFlow: Adaptive Trust Calibration for Language Model Guided Reinforcement Learning
707. NeurIPS 2026Tuning the Tuner
708. NeurIPS 2026Ultra-DPO: Reimagining LLM Alignment as a Semi-Supervised Task
709. NeurIPS 2026Uncertainty-Aware Listwise Reinforcement Fine-Tuning for Fine-Grained Visual Classification
710. NeurIPS 2026Uncertainty-Guided Reward Labeling for Reinforcement Learning under Limited Feedback
711. NeurIPS 2026Underlying Functional Structure of Reinforcement Learning
712. NeurIPS 2026Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning
713. NeurIPS 2026Unlearning Diffusion Policies via Relative Fisher Forgetting
714. NeurIPS 2026Unleashing the Power of Intrinsic-Entropy-Driven Exploration for Off-Policy Generative RL
715. NeurIPS 2026Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation
716. NeurIPS 2026Value-Priced Uncertainty: A Family of PPO-Compatible Exploration Bonuses
717. NeurIPS 2026Value-Rectified Distillation for Flow-based Offline Reinforcement Learning
718. NeurIPS 2026Variance-Adaptive Optimal Algorithm for Reinforcement Learning with MNL Function Approximation
719. NeurIPS 2026Variance-Averse n-Step Offline Reinforcement Learning for Sparse Long-Horizon Environments
720. NeurIPS 2026Variational Consequence-Driven Offline Reinforcement Learning
721. NeurIPS 2026VC-OPD: Visual Counterfactual On-Policy Distillation for Grounded Vision-Language Reasoning
722. NeurIPS 2026Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization
723. NeurIPS 2026VESPO: Variational Sequence-level Soft Policy Optimization for Off-Policy LLM Training
724. NeurIPS 2026VI-Bench: Benchmarking Prompt Inversion from AIGC Videos
725. NeurIPS 2026VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction
726. NeurIPS 2026Video Models Can Reason with Verifiable Rewards
727. NeurIPS 2026Video-FLAIR: Not Whether to Reason, But How
728. NeurIPS 2026VidHalluDoctor: Learning Video Differences to Mitigate Hallucinations in Vision-Language Models
729. NeurIPS 2026VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning
730. NeurIPS 2026VISD: Enhancing Video Reasoning via Structured Self-Distillation
731. NeurIPS 2026VisionCreator-R1: A Reflection-Enhanced Native Visual-Generation Agentic Model
732. NeurIPS 2026VisionCreator-S1: Evolving Visual-Generation Agents via Skill-GRPO Optimization
733. NeurIPS 2026Visual Grounding First, Multimodal In-context Learning Follows
734. NeurIPS 2026Visual Robustness and Neural Alignment in a Shared Foraging Task: The Mouse vs. AI Benchmark
735. NeurIPS 2026Visual-ERM: Reward Modeling for Visual Equivalence
736. NeurIPS 2026VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learning
737. NeurIPS 2026VSPO: Vector-Steered Policy Optimization for Controllable Model Behavior
738. NeurIPS 2026Wasserstein residuals: Learning Gradient Flows from Population Dynamics
739. NeurIPS 2026Wayfinder: Adaptive Resource Routing from Agent Citations
740. NeurIPS 2026What Makes Two States the Same? Value-Aware State Matching for Multi-Turn Agent Credit Assignment
741. NeurIPS 2026What MLLMs Learn about When they Learn about Multimodal Reasoning
742. NeurIPS 2026When Are Compositional Problems Learnable from Verifiable Rewards?
743. NeurIPS 2026When Do Learned State Representations Break Sensitivity Analysis?
744. NeurIPS 2026When Does Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning
745. NeurIPS 2026When Does Non-Uniform Replay Matter in Reinforcement Learning?
746. NeurIPS 2026When Does Sequential Detection Collapse to a Scalar? A Necessary and Sufficient Characterisation
747. NeurIPS 2026When Must AI Training Stage Checkpoints? A Distributional Model of Durability Boundaries at Scale
748. NeurIPS 2026When Policies Cannot Be Retrained: A Unified Closed-Form View of Post-Training Steering in Offline Reinforcement Learning
749. NeurIPS 2026Where Do Long Captions Fail? Position-Aware Diagnosis and Reinforcement Learning for Detailed Image Captioning
750. NeurIPS 2026Who Should Evolve? Uncertainty-Aware Role Bottleneck Inference for Multi-Agent LLM Training

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。