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 12 / 33 页

551. ICML 2025Distributionally Robust Multi-Agent Reinforcement Learning for Dynamic Chute Mapping
552. ICML 2025Distributionally Robust Policy Learning under Concept Drifts
553. ICML 2025Diversifying Robot Locomotion Behaviors with Extrinsic Behavioral Curiosity
554. ICML 2025Diversity By Design: Leveraging Distribution Matching for Offline Model-Based Optimization
555. ICML 2025Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning
556. ICML 2025Diving into Self-Evolving Training for Multimodal Reasoning
557. ICML 2025Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective
558. ICML 2025DPO Meets PPO: Reinforced Token Optimization for RLHF
559. ICML 2025DSBRouter: End-to-end Global Routing via Diffusion Schr\"{o}dinger Bridge
560. ICML 2025EARL-BO: Reinforcement Learning for Multi-Step Lookahead, High-Dimensional Bayesian Optimization
561. ICML 2025Efficient Online Reinforcement Learning for Diffusion Policy
562. ICML 2025Efficient Skill Discovery via Regret-Aware Optimization
563. ICML 2025EGPlace: An Efficient Macro Placement Method via Evolutionary Search with Greedy Repositioning Guided Mutation
564. ICML 2025ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics
565. ICML 2025Eliciting Language Model Behaviors with Investigator Agents
566. ICML 2025Embedding Safety into RL: A New Take on Trust Region Methods
567. ICML 2025Empirical Design in Reinforcement Learning
568. ICML 2025Enabling Optimal Decisions in Rehearsal Learning under CARE Condition
569. ICML 2025Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration
570. ICML 2025Enhancing Decision-Making of Large Language Models via Actor-Critic
571. ICML 2025Enhancing Diversity In Parallel Agents: A Maximum State Entropy Exploration Story
572. ICML 2025Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language Models
573. ICML 2025Ergodic Generative Flows
574. ICML 2025EvoControl: Multi-Frequency Bi-Level Control for High-Frequency Continuous Control
575. ICML 2025EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration
576. ICML 2025Exact Recovery of Sparse Binary Vectors from Generalized Linear Measurements
577. ICML 2025Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal Representations
578. ICML 2025Explicit Exploration for High-Welfare Equilibria in Game-Theoretic Multiagent Reinforcement Learning
579. ICML 2025Explicit Preference Optimization: No Need for an Implicit Reward Model
580. ICML 2025Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher Sampling
581. ICML 2025Extreme Value Policy Optimization for Safe Reinforcement Learning
582. ICML 2025Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments
583. ICML 2025Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean Field Games
584. ICML 2025Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning
585. ICML 2025Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples
586. ICML 2025Flow Q-Learning
587. ICML 2025Flow-based Domain Randomization for Learning and Sequencing Robotic Skills
588. ICML 2025Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through Options
589. ICML 2025FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making
590. ICML 2025Gap-Dependent Bounds for Federated $Q$-Learning
591. ICML 2025General agents need world models
592. ICML 2025GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation
593. ICML 2025Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning
594. ICML 2025GoIRL: Graph-Oriented Inverse Reinforcement Learning for Multimodal Trajectory Prediction
595. ICML 2025Gradient Boosting Reinforcement Learning
596. ICML 2025GradPS: Resolving Futile Neurons in Parameter Sharing Network for Multi-Agent Reinforcement Learning
597. ICML 2025Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning
598. ICML 2025GRAM: A Generative Foundation Reward Model for Reward Generalization
599. ICML 2025Graph Diffusion for Robust Multi-Agent Coordination
600. ICML 2025Graph-Assisted Stitching for Offline Hierarchical Reinforcement Learning

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。