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 22 / 24 页

1051. NeurIPS 2024Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer
1052. NeurIPS 2024PUZZLES: A Benchmark for Neural Algorithmic Reasoning
1053. NeurIPS 2024Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model
1054. NeurIPS 2024QGFN: Controllable Greediness with Action Values
1055. NeurIPS 2024QGym: Scalable Simulation and Benchmarking of Queuing Network Controllers
1056. NeurIPS 2024RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning
1057. NeurIPS 2024Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces
1058. NeurIPS 2024Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation
1059. NeurIPS 2024Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning
1060. NeurIPS 2024Real-Time Recurrent Learning using Trace Units in Reinforcement Learning
1061. NeurIPS 2024REBEL: Reinforcement Learning via Regressing Relative Rewards
1062. NeurIPS 2024REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR
1063. NeurIPS 2024Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents
1064. NeurIPS 2024Recurrent Reinforcement Learning with Memoroids
1065. NeurIPS 2024Recursive Introspection: Teaching Language Model Agents How to Self-Improve
1066. NeurIPS 2024Regularized Conditional Diffusion Model for Multi-Task Preference Alignment
1067. NeurIPS 2024Regularized Q-Learning
1068. NeurIPS 2024Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
1069. NeurIPS 2024Reinforced Cross-Domain Knowledge Distillation on Time Series Data
1070. NeurIPS 2024Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers
1071. NeurIPS 2024Reinforcement Learning Guided Semi-Supervised Learning
1072. NeurIPS 2024Reinforcement Learning Policy as Macro Regulator Rather than Macro Placer
1073. NeurIPS 2024Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity
1074. NeurIPS 2024Reinforcement Learning with Adaptive Regularization for Safe Control of Critical Systems
1075. NeurIPS 2024Reinforcement Learning with Euclidean Data Augmentation for State-Based Continuous Control
1076. NeurIPS 2024Reinforcement Learning with Lookahead Information
1077. NeurIPS 2024Reinforcement Learning with LTL and $\omega$-Regular Objectives via Optimality-Preserving Translation to Average Rewards
1078. NeurIPS 2024Reinforcing LLM Agents via Policy Optimization with Action Decomposition
1079. NeurIPS 2024Relating Hopfield Networks to Episodic Control
1080. NeurIPS 2024ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search
1081. NeurIPS 2024Rethinking Exploration in Reinforcement Learning with Effective Metric-Based Exploration Bonus
1082. NeurIPS 2024Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment
1083. NeurIPS 2024Rethinking Model-based, Policy-based, and Value-based Reinforcement Learning via the Lens of Representation Complexity
1084. NeurIPS 2024Rethinking Optimal Transport in Offline Reinforcement Learning
1085. NeurIPS 2024Reward Machines for Deep RL in Noisy and Uncertain Environments
1086. NeurIPS 2024RGMDT: Return-Gap-Minimizing Decision Tree Extraction in Non-Euclidean Metric Space
1087. NeurIPS 2024Risk-Averse Fine-tuning of Large Language Models
1088. NeurIPS 2024Risk-sensitive control as inference with Rényi divergence
1089. NeurIPS 2024RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation
1090. NeurIPS 2024RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold
1091. NeurIPS 2024RL-GPT: Integrating Reinforcement Learning and Code-as-policy
1092. NeurIPS 2024Robot Policy Learning with Temporal Optimal Transport Reward
1093. NeurIPS 2024Robust Reinforcement Learning from Corrupted Human Feedback
1094. NeurIPS 2024Robust Reinforcement Learning with General Utility
1095. NeurIPS 2024ROIDICE: Offline Return on Investment Maximization for Efficient Decision Making
1096. NeurIPS 2024RoME: A Robust Mixed-Effects Bandit Algorithm for Optimizing Mobile Health Interventions
1097. NeurIPS 2024Rule Based Rewards for Language Model Safety
1098. NeurIPS 2024Safe and Efficient: A Primal-Dual Method for Offline Convex CMDPs under Partial Data Coverage
1099. NeurIPS 2024Safety through feedback in Constrained RL
1100. NeurIPS 2024Sample Complexity Reduction via Policy Difference Estimation in Tabular 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。