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 784 篇，第 3 / 16 页

101. NeurIPS 2025Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning
102. NeurIPS 2025COGNAC: Cooperative Graph-based Networked Agent Challenges for Multi-Agent Reinforcement Learning
103. NeurIPS 2025Cognitive Predictive Processing: A Human-inspired Framework for Adaptive Exploration in Open-World Reinforcement Learning
104. NeurIPS 2025COLA: Towards Efficient Multi-Objective Reinforcement Learning with Conflict Objective Regularization in Latent Space
105. NeurIPS 2025Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning
106. NeurIPS 2025Complexity Scaling Laws for Neural Models using Combinatorial Optimization
107. NeurIPS 2025Composing Linear Layers from Irreducibles
108. NeurIPS 2025Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Data
109. NeurIPS 2025Compositional Monte Carlo Tree Diffusion for Extendable Planning
110. NeurIPS 2025Computational Hardness of Reinforcement Learning with Partial $q^{\pi}$-Realizability
111. NeurIPS 2025Compute-Optimal Scaling for Value-Based Deep RL
112. NeurIPS 2025Conditioning Matters: Training Diffusion Policies is Faster Than You Think
113. NeurIPS 2025Conformal Prediction Beyond the Horizon: Distribution-Free Inference for Policy Evaluation
114. NeurIPS 2025Confounding Robust Deep Reinforcement Learning: A Causal Approach
115. NeurIPS 2025Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning
116. NeurIPS 2025Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning
117. NeurIPS 2025Constrained Best Arm Identification
118. NeurIPS 2025Constrained Optimization From a Control Perspective via Feedback Linearization
119. NeurIPS 2025Constructing an Optimal Behavior Basis for the Option Keyboard
120. NeurIPS 2025Contextual Integrity in LLMs via Reasoning and Reinforcement Learning
121. NeurIPS 2025Contextual Online Pricing with (Biased) Offline Data
122. NeurIPS 2025Continual Knowledge Adaptation for Reinforcement Learning
123. NeurIPS 2025Continuous Q-Score Matching: Diffusion Guided Reinforcement Learning for Continuous-Time Control
124. NeurIPS 2025Continuous Soft Actor-Critic: An Off-Policy Learning Method Robust to Time Discretization
125. NeurIPS 2025Convergence Theorems for Entropy-Regularized and Distributional Reinforcement Learning
126. NeurIPS 2025Convergent Functions, Divergent Forms
127. NeurIPS 2025CORE: Collaborative Optimization with Reinforcement Learning and Evolutionary Algorithm for Floorplanning
128. NeurIPS 2025Counteractive RL: Rethinking Core Principles for Efficient and Scalable Deep Reinforcement Learning
129. NeurIPS 2025CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models
130. NeurIPS 2025CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning
131. NeurIPS 2025Ctrl-DNA: Controllable Cell-Type-Specific Regulatory DNA Design via Constrained RL
132. NeurIPS 2025CURE: Co-Evolving Coders and Unit Testers via Reinforcement Learning
133. NeurIPS 2025Curriculum Design for Trajectory-Constrained Agent: Compressing Chain-of-Thought Tokens in LLMs
134. NeurIPS 2025CURV: Coherent Uncertainty-Aware Reasoning in Vision-Language Models for X-Ray Report Generation
135. NeurIPS 2025Curvature Tuning: Provable Training-free Model Steering From a Single Parameter
136. NeurIPS 2025Cypher-RI: Reinforcement Learning for Integrating Schema Selection into Cypher Generation
137. NeurIPS 2025d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning
138. NeurIPS 2025DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning
139. NeurIPS 2025DAPO : Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage-Based Policy Optimization
140. NeurIPS 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scale
141. NeurIPS 2025DCcluster-Opt: Benchmarking Dynamic Multi-Objective Optimization for Geo-Distributed Data Center Workloads
142. NeurIPS 2025DEAL: Diffusion Evolution Adversarial Learning for Sim-to-Real Transfer
143. NeurIPS 2025Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation
144. NeurIPS 2025Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments
145. NeurIPS 2025DeepDiver: Adaptive Web-Search Intensity Scaling via Reinforcement Learning
146. NeurIPS 2025DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO
147. NeurIPS 2025Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO
148. NeurIPS 2025Deployment Efficient Reward-Free Exploration with Linear Function Approximation
149. NeurIPS 2025DesignX: Human-Competitive Algorithm Designer for Black-Box Optimization
150. NeurIPS 2025DexFlyWheel: A Scalable and Self-improving Data Generation Framework for Dexterous Manipulation

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。