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 1,190 篇，第 10 / 24 页

451. ICML 2024Exploration and Anti-Exploration with Distributional Random Network Distillation
452. ICML 2024Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization
453. ICML 2024Exploring the LLM Journey from Cognition to Expression with Linear Representations
454. ICML 2024Factored-Reward Bandits with Intermediate Observations
455. ICML 2024Failures Are Fated, But Can Be Faded: Characterizing and Mitigating Unwanted Behaviors in Large-Scale Vision and Language Models
456. ICML 2024Fair Off-Policy Learning from Observational Data
457. ICML 2024Fair Resource Allocation in Multi-Task Learning
458. ICML 2024Fast Decision Boundary based Out-of-Distribution Detector
459. ICML 2024Feasibility Consistent Representation Learning for Safe Reinforcement Learning
460. ICML 2024Feasible Reachable Policy Iteration
461. ICML 2024Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices
462. ICML 2024Feedback Efficient Online Fine-Tuning of Diffusion Models
463. ICML 2024FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning
464. ICML 2024Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning
465. ICML 2024Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
466. ICML 2024Finite Time Logarithmic Regret Bounds for Self-Tuning Regulation
467. ICML 2024Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning
468. ICML 2024Foundation Policies with Hilbert Representations
469. ICML 2024Fourier Controller Networks for Real-Time Decision-Making in Embodied Learning
470. ICML 2024From Biased Selective Labels to Pseudo-Labels: An Expectation-Maximization Framework for Learning from Biased Decisions
471. ICML 2024From Generalization Analysis to Optimization Designs for State Space Models
472. ICML 2024From Inverse Optimization to Feasibility to ERM
473. ICML 2024From Neurons to Neutrons: A Case Study in Interpretability
474. ICML 2024From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems
475. ICML 2024From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning
476. ICML 2024Fully-Dynamic Approximate Decision Trees With Worst-Case Update Time Guarantees
477. ICML 2024Fundamental Limitations of Alignment in Large Language Models
478. ICML 2024FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning
479. ICML 2024Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction
480. ICML 2024GFlowNet Training by Policy Gradients
481. ICML 2024Global Reinforcement Learning : Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods
482. ICML 2024Hard Tasks First: Multi-Task Reinforcement Learning Through Task Scheduling
483. ICML 2024HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning
484. ICML 2024HarmonyDream: Task Harmonization Inside World Models
485. ICML 2024HGAP: Boosting Permutation Invariant and Permutation Equivariant in Multi-Agent Reinforcement Learning via Graph Attention Network
486. ICML 2024HGCN2SP: Hierarchical Graph Convolutional Network for Two-Stage Stochastic Programming
487. ICML 2024Hieros: Hierarchical Imagination on Structured State Space Sequence World Models
488. ICML 2024How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?
489. ICML 2024How Does Goal Relabeling Improve Sample Efficiency?
490. ICML 2024How to Explore with Belief: State Entropy Maximization in POMDPs
491. ICML 2024How to Leverage Diverse Demonstrations in Offline Imitation Learning
492. ICML 2024Human Alignment of Large Language Models through Online Preference Optimisation
493. ICML 2024Hybrid Inverse Reinforcement Learning
494. ICML 2024Hybrid Reinforcement Learning from Offline Observation Alone
495. ICML 2024Implicit Bias of Policy Gradient in Linear Quadratic Control: Extrapolation to Unseen Initial States
496. ICML 2024Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements
497. ICML 2024Improving Generalization in Offline Reinforcement Learning via Adversarial Data Splitting
498. ICML 2024Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games
499. ICML 2024Improving Token-Based World Models with Parallel Observation Prediction
500. ICML 2024In value-based deep reinforcement learning, a pruned network is a good network

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。