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 6,885 篇，第 111 / 138 页

5501. NeurIPS 2024Finding good policies in average-reward Markov Decision Processes without prior knowledge
5502. NeurIPS 2024Fine Tuning Out-of-Vocabulary Item Recommendation with User Sequence Imagination
5503. NeurIPS 2024Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning
5504. NeurIPS 2024First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs
5505. NeurIPS 2024FLAME : Factuality-Aware Alignment for Large Language Models
5506. NeurIPS 2024FlexPlanner: Flexible 3D Floorplanning via Deep Reinforcement Learning in Hybrid Action Space with Multi-Modality Representation
5507. NeurIPS 2024Flipping-based Policy for Chance-Constrained Markov Decision Processes
5508. NeurIPS 2024Focus On What Matters: Separated Models For Visual-Based RL Generalization
5509. NeurIPS 2024Foundations of Multivariate Distributional Reinforcement Learning
5510. NeurIPS 2024From Text to Trajectory: Exploring Complex Constraint Representation and Decomposition in Safe Reinforcement Learning
5511. NeurIPS 2024Functional Bilevel Optimization for Machine Learning
5512. NeurIPS 2024GarmentLab: A Unified Simulation and Benchmark for Garment Manipulation
5513. NeurIPS 2024Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization
5514. NeurIPS 2024Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search
5515. NeurIPS 2024GenRL: Multimodal-foundation world models for generalization in embodied agents
5516. NeurIPS 2024Geometric-Averaged Preference Optimization for Soft Preference Labels
5517. NeurIPS 2024Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment
5518. NeurIPS 2024Goal Conditioned Reinforcement Learning for Photo Finishing Tuning
5519. NeurIPS 2024Goal-Conditioned On-Policy Reinforcement Learning
5520. NeurIPS 2024Going Beyond Heuristics by Imposing Policy Improvement as a Constraint
5521. NeurIPS 2024GOMAA-Geo: GOal Modality Agnostic Active Geo-localization
5522. NeurIPS 2024Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
5523. NeurIPS 2024Gradient-Free Methods for Nonconvex Nonsmooth Stochastic Compositional Optimization
5524. NeurIPS 2024Graph Diffusion Policy Optimization
5525. NeurIPS 2024Graph Learning for Numeric Planning
5526. NeurIPS 2024Grounded Answers for Multi-agent Decision-making Problem through Generative World Model
5527. NeurIPS 2024Grounding Multimodal Large Language Models in Actions
5528. NeurIPS 2024Group Robust Preference Optimization in Reward-free RLHF
5529. NeurIPS 2024GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning
5530. NeurIPS 2024GUIDE: Real-Time Human-Shaped Agents
5531. NeurIPS 2024Hierarchical Programmatic Option Framework
5532. NeurIPS 2024How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach
5533. NeurIPS 2024How to Solve Contextual Goal-Oriented Problems with Offline Datasets?
5534. NeurIPS 2024HumanVLA: Towards Vision-Language Directed Object Rearrangement by Physical Humanoid
5535. NeurIPS 2024Hybrid Reinforcement Learning Breaks Sample Size Barriers In Linear MDPs
5536. NeurIPS 2024Identifying Latent State-Transition Processes for Individualized Reinforcement Learning
5537. NeurIPS 2024Identifying Selections for Unsupervised Subtask Discovery
5538. NeurIPS 2024Imitating Language via Scalable Inverse Reinforcement Learning
5539. NeurIPS 2024Implicit Curriculum in Procgen Made Explicit
5540. NeurIPS 2024Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn
5541. NeurIPS 2024Improving Environment Novelty Quantification for Effective Unsupervised Environment Design
5542. NeurIPS 2024In-Trajectory Inverse Reinforcement Learning: Learn Incrementally Before an Ongoing Trajectory Terminates
5543. NeurIPS 2024Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptation
5544. NeurIPS 2024InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
5545. NeurIPS 2024Integrating Suboptimal Human Knowledge with Hierarchical Reinforcement Learning for Large-Scale Multiagent Systems
5546. NeurIPS 2024Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents
5547. NeurIPS 2024Interpreting Learned Feedback Patterns in Large Language Models
5548. NeurIPS 2024Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
5549. NeurIPS 2024Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?
5550. NeurIPS 2024Is O(log N) practical? Near-Equivalence Between Delay Robustness and Bounded Regret in Bandits and RL

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。