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 784 篇，第 12 / 16 页

551. NeurIPS 2025Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models
552. NeurIPS 2025ReMA: Learning to Meta-Think for LLMs with Multi-agent Reinforcement Learning
553. NeurIPS 2025Rendering-Aware Reinforcement Learning for Vector Graphics Generation
554. NeurIPS 2025RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language Models
555. NeurIPS 2025ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
556. NeurIPS 2025ResponseRank: Data-Efficient Reward Modeling through Preference Strength Learning
557. NeurIPS 2025Rethinking Verification for LLM Code Generation: From Generation to Testing
558. NeurIPS 2025Retro-R1: LLM-based Agentic Retrosynthesis
559. NeurIPS 2025Retrospective In-Context Learning for Temporal Credit Assignment with Large Language Models
560. NeurIPS 2025Retrosynthesis Planning via Worst-path Policy Optimisation in Tree-structured MDPs
561. NeurIPS 2025Retrv-R1: A Reasoning-Driven MLLM Framework for Universal and Efficient Multimodal Retrieval
562. NeurIPS 2025Reverse Engineering Human Preferences with Reinforcement Learning
563. NeurIPS 2025Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective
564. NeurIPS 2025Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
565. NeurIPS 2025Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models
566. NeurIPS 2025Revolutionizing Training-Free NAS: Towards Efficient Automatic Proxy Discovery via Large Language Models
567. NeurIPS 2025Reward Reasoning Models
568. NeurIPS 2025Reward-Aware Proto-Representations in Reinforcement Learning
569. NeurIPS 2025Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generation
570. NeurIPS 2025RF-Agent: Automated Reward Function Design via Language Agent Tree Search
571. NeurIPS 2025Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization
572. NeurIPS 2025Risk-Averse Constrained Reinforcement Learning with Optimized Certainty Equivalents
573. NeurIPS 2025Risk-Averse Total-Reward Reinforcement Learning
574. NeurIPS 2025RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning
575. NeurIPS 2025RLGF: Reinforcement Learning with Geometric Feedback for Autonomous Driving Video Generation
576. NeurIPS 2025RLVR-World: Training World Models with Reinforcement Learning
577. NeurIPS 2025RLZero: Direct Policy Inference from Language Without In-Domain Supervision
578. NeurIPS 2025RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics
579. NeurIPS 2025Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics
580. NeurIPS 2025RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skills
581. NeurIPS 2025Robust and Diverse Multi-Agent Learning via Rational Policy Gradient
582. NeurIPS 2025Robust and Scalable Autonomous Reinforcement Learning in Irreversible Environments
583. NeurIPS 2025Robust LLM Alignment via Distributionally Robust Direct Preference Optimization
584. NeurIPS 2025Robust Policy Expansion for Offline-to-Online RL under Diverse Data Corruption
585. NeurIPS 2025Robust Reinforcement Learning in Finance: Modeling Market Impact with Elliptic Uncertainty Sets
586. NeurIPS 2025Role-aware Multi-agent Reinforcement Learning for Coordinated Emergency Traffic Control
587. NeurIPS 2025Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning
588. NeurIPS 2025RULE: Reinforcement UnLEarning Achieves Forget-retain Pareto Optimality
589. NeurIPS 2025S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models
590. NeurIPS 2025Safe and Stable Control via Lyapunov-Guided Diffusion Models
591. NeurIPS 2025Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
592. NeurIPS 2025SAFE: Multitask Failure Detection for Vision-Language-Action Models
593. NeurIPS 2025SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
594. NeurIPS 2025SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation
595. NeurIPS 2025SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning
596. NeurIPS 2025Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning
597. NeurIPS 2025Sample-Efficient Tabular Self-Play for Offline Robust Reinforcement Learning
598. NeurIPS 2025SAMPO: Scale-wise Autoregression with Motion Prompt for Generative World Models
599. NeurIPS 2025SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning
600. NeurIPS 2025Scaffolding Dexterous Manipulation with Vision-Language Models

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。