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 2,494 篇，第 12 / 50 页

551. NeurIPS 2026RILA: A Radar-Native Structured Interface from Sparse mmWave Point Clouds to Large Language Models
552. NeurIPS 2026Risk-Aware Action Repetition via Expected Skip Evaluation
553. NeurIPS 2026Risk-Controlled Post-Processing of Decision Policies
554. NeurIPS 2026Risk-Sensitive Deep Optimal Stopping
555. NeurIPS 2026RL Excursions during Pre-training: How early is too early for on-policy learning?
556. NeurIPS 2026RL-Guided Contraction of Symbolic Tensor Networks for Quantum Circuit Equivalence
557. NeurIPS 2026RL-Guided Temporal Localization for Dual-Channel Retrieval in Long-Horizon Agent Memory
558. NeurIPS 2026RL-Inf: Tracking Non-local Training Data Influence for Online Reinforcement Learning
559. NeurIPS 2026RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models
560. NeurIPS 2026Robust Offline Reinforcement Learning against Out-of-Distribution Dynamics in Autonomous Driving
561. NeurIPS 2026Robust Policy Optimization to Prevent Catastrophic Forgetting
562. NeurIPS 2026Robust Stream Classification using Time Neutralising Decision Trees
563. NeurIPS 2026Robust-by-Design Distributional Learning from Contaminated Samples
564. NeurIPS 2026ROLLVERIFY: BRIDGING EFFICIENCY AND ACCURACY IN LONG-TAIL ROLLOUT REINFORCEMENT LEARNING
565. NeurIPS 2026Rotations on Latent Hyperspheres: a Geometry-Aware Guiding Framework for Diffusion Models
566. NeurIPS 2026Rubric-Align: Safety Alignment through Dynamically Co-Evolving Rubrics
567. NeurIPS 2026S$^2$-RL: Sample-Set Dual Reinforcement Learning for Generative Semantic Segmentation Dataset Distillation
568. NeurIPS 2026S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF
569. NeurIPS 2026Safe Offline Reinforcement Learning using Behavior Regularisation and Latent Feasibility-Guidance
570. NeurIPS 2026Safe Score Matching: Diffusion Policies with Hamilton-Jacobi Reachability for Online Safe Reinforcement Learning
571. NeurIPS 2026Safe-Fair MACPO: Burden-Fair Constrained Policy Optimization for Safe Multi-Agent Reinforcement Learning
572. NeurIPS 2026SafePro: Generation of Safe and Functional Proteins via Cross-Task Conflict-Aware Alignment
573. NeurIPS 2026SAIR: Cost-Efficient Multi-Stage ML Pipeline Autoscaling via In-Context Reinforcement Learning
574. NeurIPS 2026Same Words, Different Judgments: How Preferences Vary Across Modalities
575. NeurIPS 2026Sampling-Based Safe Reinforcement Learning
576. NeurIPS 2026SAMPPO: Structure-Aware Mirror Proximal Policy Optimization
577. NeurIPS 2026Scalable Minimal-Change Learning for Controllable Image Editing
578. NeurIPS 2026Scalable Multi-Agent Contrastive Reinforcement Learning
579. NeurIPS 2026SceneFactory: GPU-Accelerated Multi-Agent Driving Simulation with Physics-Based Vehicle Dynamics
580. NeurIPS 2026Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models
581. NeurIPS 2026SD-Search: Hindsight Self-Distillation for Search-Augmented Reasoning
582. NeurIPS 2026SEAR: Sample Efficient Action Chunking Reinforcement Learning
583. NeurIPS 2026Seeing but Not Detecting: Privacy-Preserving Scene Text Attack via Hybrid Adversarial Policy Learning
584. NeurIPS 2026Selective Off-Policy Reference Tuning with Plan Guidance
585. NeurIPS 2026Self-Calibrated GUI Reward Model via Inverse Dynamic Modeling
586. NeurIPS 2026Self-Correction as Transition Geometry: Internalizing Reasoning via Lifted State Policy Optimization
587. NeurIPS 2026Self-Distilled RLVR
588. NeurIPS 2026Self-Evolution Reasoner: Continuous Optimization via Policy-Intrinsic Exploration and Exploitation
589. NeurIPS 2026Self-Evolving Agents Should Build Internal and External Models of the World
590. NeurIPS 2026Self-Improvement Imitation with Biologically Guided Search for Protein Design Under Oracle Budgets
591. NeurIPS 2026Self-Supervised On-Policy Reinforcement Learning via Contrastive Proximal Policy Optimisation
592. NeurIPS 2026SelfCritic-VLA: Language as Intrinsic Critic for Vision Language Action Models in Autonomous Driving
593. NeurIPS 2026Serialization Tax in Shared-Latent Exchangeable Decisions
594. NeurIPS 2026SETA: Scaling Environments for Terminal Agents
595. NeurIPS 2026SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
596. NeurIPS 2026Shared Modular Recurrence in Contextual MDPs for Universal Morphology Control
597. NeurIPS 2026Sharper Guarantees for Misspecified Kernelized Bandit Optimization
598. NeurIPS 2026Signal-Adaptive Trust Regions for Gradient-Free Optimization of Recurrent Spiking Neural Networks
599. NeurIPS 2026Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators
600. NeurIPS 2026Simulation-aided Reinforcement Learning with Control Variates

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。