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 1,021 篇，第 14 / 21 页

651. ICML 2026Prioritize the Process, Not Just the Outcome: Rewarding Latent Thought Trajectories Improves Reasoning in Looped Language Models
652. ICML 2026Prioritized Model Experience Replay
653. ICML 2026PRISM: Demystifying Retention and Interaction in Mid-Training
654. ICML 2026Privileged Information Distillation for Language Models
655. ICML 2026PRM-PBE: Process Reward Model for Reinforcement Learning in Programming-by-Example
656. ICML 2026Probabilistic Performance Guarantees for Multi-Task Reinforcement Learning
657. ICML 2026Probing RLVR Training Instability through the Lens of Objective-Level Hacking
658. ICML 2026Procedural Generation Of Algorithm Discovery Tasks in Machine Learning
659. ICML 2026PromptPilot: Game-Theoretic Multi-Agent Prompt Optimization for Segment Anything
660. ICML 2026PromptRL: Prompt Matters in RL for Flow-Based Image Generation
661. ICML 2026ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation
662. ICML 2026Provable Benefits of RLVR over SFT for Reasoning Models: Learning to Backtrack Efficiently
663. ICML 2026Provable Sample Efficiency of Curriculum Post-Training for Transformer Reasoning
664. ICML 2026Provably Convergent Actor-Critic for MARL through Risk-aversion
665. ICML 2026Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning
666. ICML 2026PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake Detection
667. ICML 2026PS-PPO : Prefix-Sampling PPO for Critic-Free RLHF
668. ICML 2026Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization
669. ICML 2026PyVision-RL: Forging Open Agentic Vision Models via RL
670. ICML 2026Q-Flow: Stable and Expressive Reinforcement Learning with Flow-based Policy
671. ICML 2026Q-SAM: Unlocking Sharpness-Aware Minimization for Generalization in Offline Reinforcement Learning
672. ICML 2026QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL
673. ICML 2026Quantifying and Optimizing Simplicity via Polynomial Representations
674. ICML 2026Quantum Robust Inner Minimization for Reinforcement Learning with Quadratic Speed-Up in Query Complexity
675. ICML 2026QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning
676. ICML 2026R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training
677. ICML 2026R1-SyntheticVL: Is Synthetic Data from Generative Models Ready for Multimodal Large Language Model?
678. ICML 2026R2R2: Robust Representation for Intensive Experience Reuse via Redundancy Reduction in Self-Predictive Learning
679. ICML 2026RAD: Retrieval High-quality Demonstrations to Enhance Decision-making
680. ICML 2026RAGEN-2: Reasoning Collapse in Agentic RL
681. ICML 2026RAMAC: Multimodal Risk-Aware Offline Reinforcement Learning and the Role of Behavior Regularization
682. ICML 2026Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation
683. ICML 2026RAST-MoE-RL: A Regime-Aware Spatio-Temporal MoE Framework for Deep Reinforcement Learning in Ride-Hailing
684. ICML 2026Rate or Fate? RLV$^{\varepsilon}$R: Reinforcement Learning with Verifiable Noisy Rewards
685. ICML 2026Ratio-Variance Regularized Policy Optimization
686. ICML 2026Rationality Measurement and Theory for Reinforcement Learning Agents
687. ICML 2026Real-Time Aligned Reward Model beyond Semantics
688. ICML 2026REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge
689. ICML 2026Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL
690. ICML 2026Reasoning-VLA: An Efficient and Spatial-Guided General Vision-Language-Action Reasoning Model for Autonomous Driving
691. ICML 2026ReAugment: Targeted Few-Shot Time Series Augmentation via Model Zoo-Guided Reinforcement Learning
692. ICML 2026Recontextualization Mitigates Specification Gaming Without Modifying the Specification
693. ICML 2026Recovering Hidden Reward in Diffusion-Based Policies
694. ICML 2026Recurrent Equivariant Constraint Modulation: Learning Per-Layer Symmetry Relaxation from Data
695. ICML 2026Recurrent Structural Policy Gradient for Partially Observable Mean Field Games
696. ICML 2026Refined Analysis of Entropy-Regularized Actor-Critic
697. ICML 2026Reflect-then-Correct: Rebalancing Task Optimization for Generalizable Meta-Reinforcement Learning via Distributional Value Error Reduction
698. ICML 2026Reflector: Internalizing Step-wise Reflection against Indirect Jailbreaks
699. ICML 2026REG: In-Sample RL via Regularizing the Evaluation Gap
700. ICML 2026Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief

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。