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 18 / 24 页

851. NeurIPS 2024Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate
852. NeurIPS 2024Efficient Reinforcement Learning by Discovering Neural Pathways
853. NeurIPS 2024Embedding-Aligned Language Models
854. NeurIPS 2024Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity
855. NeurIPS 2024Enhancing Chess Reinforcement Learning with Graph Representation
856. NeurIPS 2024Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation
857. NeurIPS 2024Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control
858. NeurIPS 2024Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent Approach
859. NeurIPS 2024Enhancing Robustness of Graph Neural Networks on Social Media with Explainable Inverse Reinforcement Learning
860. NeurIPS 2024Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning
861. NeurIPS 2024EpiCare: A Reinforcement Learning Benchmark for Dynamic Treatment Regimes
862. NeurIPS 2024Episodic Future Thinking Mechanism for Multi-agent Reinforcement Learning
863. NeurIPS 2024Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking
864. NeurIPS 2024Exclusively Penalized Q-learning for Offline Reinforcement Learning
865. NeurIPS 2024Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation Mismatch
866. NeurIPS 2024Exploiting the Replay Memory Before Exploring the Environment: Enhancing Reinforcement Learning Through Empirical MDP Iteration
867. NeurIPS 2024Exploration by Learning Diverse Skills through Successor State Representations
868. NeurIPS 2024Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following
869. NeurIPS 2024Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement Learning
870. NeurIPS 2024FactorSim: Generative Simulation via Factorized Representation
871. NeurIPS 2024Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learning
872. NeurIPS 2024Federated Ensemble-Directed Offline Reinforcement Learning
873. NeurIPS 2024Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning
874. NeurIPS 2024Feint Behaviors and Strategies: Formalization, Implementation and Evaluation
875. NeurIPS 2024Few-Shot Task Learning through Inverse Generative Modeling
876. NeurIPS 2024Finding good policies in average-reward Markov Decision Processes without prior knowledge
877. NeurIPS 2024Fine Tuning Out-of-Vocabulary Item Recommendation with User Sequence Imagination
878. NeurIPS 2024Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning
879. NeurIPS 2024First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs
880. NeurIPS 2024FLAME : Factuality-Aware Alignment for Large Language Models
881. NeurIPS 2024FlexPlanner: Flexible 3D Floorplanning via Deep Reinforcement Learning in Hybrid Action Space with Multi-Modality Representation
882. NeurIPS 2024Flipping-based Policy for Chance-Constrained Markov Decision Processes
883. NeurIPS 2024Focus On What Matters: Separated Models For Visual-Based RL Generalization
884. NeurIPS 2024Foundations of Multivariate Distributional Reinforcement Learning
885. NeurIPS 2024From Text to Trajectory: Exploring Complex Constraint Representation and Decomposition in Safe Reinforcement Learning
886. NeurIPS 2024Functional Bilevel Optimization for Machine Learning
887. NeurIPS 2024GarmentLab: A Unified Simulation and Benchmark for Garment Manipulation
888. NeurIPS 2024Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization
889. NeurIPS 2024Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search
890. NeurIPS 2024GenRL: Multimodal-foundation world models for generalization in embodied agents
891. NeurIPS 2024Geometric-Averaged Preference Optimization for Soft Preference Labels
892. NeurIPS 2024Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment
893. NeurIPS 2024Goal Conditioned Reinforcement Learning for Photo Finishing Tuning
894. NeurIPS 2024Goal-Conditioned On-Policy Reinforcement Learning
895. NeurIPS 2024Going Beyond Heuristics by Imposing Policy Improvement as a Constraint
896. NeurIPS 2024GOMAA-Geo: GOal Modality Agnostic Active Geo-localization
897. NeurIPS 2024Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
898. NeurIPS 2024Gradient-Free Methods for Nonconvex Nonsmooth Stochastic Compositional Optimization
899. NeurIPS 2024Graph Diffusion Policy Optimization
900. NeurIPS 2024Graph Learning for Numeric Planning

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。