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 17 / 21 页

801. ICML 2026Seeing is Solving: Unlocking Efficient Multimodal RL via View Alignment
802. ICML 2026Segment-Aligned Policy Optimization for Multi-Modal Reasoning
803. ICML 2026Self-CriTeach: LLM Self-Teaching and Self-Critiquing for Improving Robotic Planning via Automated Domain Generation
804. ICML 2026Self-Distillation Enables Continual Learning
805. ICML 2026Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
806. ICML 2026Self-evolving LLM agents with in-distribution Optimization
807. ICML 2026Self-supervised Hierarchical Visual Reasoning with World Model
808. ICML 2026SemRep : Generative Code Representation Learning with Code Transformations
809. ICML 2026SERA: Soft-Verified Efficient Repository Agents
810. ICML 2026SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning
811. ICML 2026SHAP-Guided Kernel Actor-Critic for Explainable Reinforcement Learning
812. ICML 2026Short Chains, Deep Thoughts: Balancing Reasoning Efficiency and Intra-Segment Capability via Split-Merge Optimization
813. ICML 2026Shrinking the Variance: Shrinkage Baselines for Reinforcement Learning with Verifiable Rewards
814. ICML 2026SIGMA-PPG: Statistical-prior Informed Generative Masking Architecture for PPG Foundation Model
815. ICML 2026Signature-Informed Transformer for Asset Allocation
816. ICML 2026Sim2Reason: Solving Physics Olympiad via Reinforcement Learning on Physics Simulators
817. ICML 2026Simple Policy Gradients for Reasoning with Diffusion Language Models
818. ICML 2026Simultaneous Speech-to-Speech Translation Without Aligned Data
819. ICML 2026Single-Rollout Hidden-State Dynamics for Training-Free RLVR Data Selection
820. ICML 2026Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
821. ICML 2026SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning
822. ICML 2026SMAC: Score-Matched Actor-Critics for Robust Offline-to-Online Transfer
823. ICML 2026Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models
824. ICML 2026Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO
825. ICML 2026SOLAR for Offline MARL: Plateau-Triggered Potential Shaping under World-Model Uncertainty
826. ICML 2026Solving the Offline and Online Min-Max Problem of Non-smooth Submodular-Concave Functions: A Zeroth-Order Approach
827. ICML 2026SPAR: Support-Preserving Action Rectification
828. ICML 2026SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs
829. ICML 2026Sparse Topology-Aware Pairwise Scoring for Large-Scale Multi-Agent Reinforcement Learning
830. ICML 2026SpatialReward: Bridging the Perception Gap in Online RL for Image Editing via Explicit Spatial Reasoning
831. ICML 2026Spectral Collapse Drives Loss of Plasticity in Deep Continual Learning
832. ICML 2026Spectral Flow Matching: Stabilizing Stochastic GFlowNets via Frequency-Domain Regularization
833. ICML 2026Speedup Patch: Learning a Plug-and-Play Policy to Accelerate Embodied Manipulation
834. ICML 2026SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning
835. ICML 2026SpikeVLA: Vision-Language-Action Models with Spiking Neural Networks
836. ICML 2026Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs
837. ICML 2026Spurious Rewards: Rethinking Training Signals in RLVR
838. ICML 2026Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning
839. ICML 2026SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning
840. ICML 2026SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning
841. ICML 2026Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers
842. ICML 2026Stabilizing PPO via Latent-Space Regularization and KDE-Driven Exploration
843. ICML 2026Stabilizing Reinforcement Learning for Diffusion Language Models
844. ICML 2026Stabilizing the Q-Gradient Field for Policy Smoothness in Actor-Critic Methods
845. ICML 2026Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs
846. ICML 2026Stable Deep Reinforcement Learning via Isotropic Gaussian Representations
847. ICML 2026Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance
848. ICML 2026STARE: Step-wise Temporal Alignment and Red-teaming Engine for Multi-modal Toxicity Attack
849. ICML 2026StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning
850. ICML 2026StitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement Learning

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。