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 1,640 篇，第 32 / 33 页

1551. NeurIPS 2025Time Reversal Symmetry for Efficient Robotic Manipulations in Deep Reinforcement Learning
1552. NeurIPS 2025Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding
1553. NeurIPS 2025To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable RL
1554. NeurIPS 2025To Think or Not To Think: A Study of Thinking in Rule-Based Visual Reinforcement Fine-Tuning
1555. NeurIPS 2025ToolRL: Reward is All Tool Learning Needs
1556. NeurIPS 2025Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper
1557. NeurIPS 2025Toward Artificial Palpation: Representation Learning of Touch on Soft Bodies
1558. NeurIPS 2025Towards Generalizable Multi-Policy Optimization with Self-Evolution for Job Scheduling
1559. NeurIPS 2025Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds
1560. NeurIPS 2025Towards Principled Unsupervised Multi-Agent Reinforcement Learning
1561. NeurIPS 2025Towards Provable Emergence of In-Context Reinforcement Learning
1562. NeurIPS 2025Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task Planning
1563. NeurIPS 2025Towards Robust Zero-Shot Reinforcement Learning
1564. NeurIPS 2025Towards Unified Multimodal Interleaved Generation via Group Relative Policy Optimization
1565. NeurIPS 2025TP-MDDN: Task-Preferenced Multi-Demand-Driven Navigation with Autonomous Decision-Making
1566. NeurIPS 2025Tracing the Representation Geometry of Language Models from Pretraining to Post-training
1567. NeurIPS 2025Train on Pins and Test on Obstacles for Rectilinear Steiner Minimum Tree
1568. NeurIPS 2025Training a Scientific Reasoning Model for Chemistry
1569. NeurIPS 2025Training Language Models to Generate Quality Code with Program Analysis Feedback
1570. NeurIPS 2025Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training
1571. NeurIPS 2025Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning
1572. NeurIPS 2025Trajectory Graph Learning: Aligning with Long Trajectories in Reinforcement Learning Without Reward Design
1573. NeurIPS 2025Tree-Guided Diffusion Planner
1574. NeurIPS 2025Tru-POMDP: Task Planning Under Uncertainty via Tree of Hypotheses and Open-Ended POMDPs
1575. NeurIPS 2025Trust Region Reward Optimization and Proximal Inverse Reward Optimization Algorithm
1576. NeurIPS 2025Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards
1577. NeurIPS 2025TTRL: Test-Time Reinforcement Learning
1578. NeurIPS 2025Turning Sand to Gold: Recycling Data to Bridge On-Policy and Off-Policy Learning via Causal Bound
1579. NeurIPS 2025UFO-RL: Uncertainty-Focused Optimization for Efficient Reinforcement Learning Data Selection
1580. NeurIPS 2025UFT: Unifying Supervised and Reinforcement Fine-Tuning
1581. NeurIPS 2025Uncertainty-Aware Multi-Objective Reinforcement Learning-Guided Diffusion Models for 3D De Novo Molecular Design
1582. NeurIPS 2025Uncertainty-aware Preference Alignment for Diffusion Policies
1583. NeurIPS 2025Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few Demonstrations
1584. NeurIPS 2025Uncertainty-Guided Exploration for Efficient AlphaZero Training
1585. NeurIPS 2025Uncertainty-quantified Rollout Policy Adaptation for Unlabelled Cross-domain Video Temporal Grounding
1586. NeurIPS 2025Uncertainty-Sensitive Privileged Learning
1587. NeurIPS 2025Understanding Data Influence in Reinforcement Finetuning
1588. NeurIPS 2025Uni-RL: Unifying Online and Offline RL via Implicit Value Regularization
1589. NeurIPS 2025UniDomain: Pretraining a Unified PDDL Domain from Real-World Demonstrations for Generalizable Robot Task Planning
1590. NeurIPS 2025Unified Reinforcement and Imitation Learning for Vision-Language Models
1591. NeurIPS 2025UniteFormer: Unifying Node and Edge Modalities in Transformers for Vehicle Routing Problems
1592. NeurIPS 2025Unlocking Multimodal Mathematical Reasoning via Process Reward Model
1593. NeurIPS 2025Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards
1594. NeurIPS 2025Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model
1595. NeurIPS 2025URB - Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles
1596. NeurIPS 2025Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought
1597. NeurIPS 2025Value Diffusion Reinforcement Learning
1598. NeurIPS 2025Value Gradient Guidance for Flow Matching Alignment
1599. NeurIPS 2025Value Improved Actor Critic Algorithms
1600. NeurIPS 2025Value-Guided Decision Transformer: A Unified Reinforcement Learning Framework for Online and Offline Settings

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。