Reinforcement Learning papers, 2023–2026

Key findings

• Reinforcement Learning went from 1,070 papers in 2023 to 2,985 in 2026, roughly 2.8x in three years.
• NeurIPS publishes the most Reinforcement Learning work: 2,494 papers from 2023 to 2026, 36% of the four-venue total.
• The fastest-growing overlap is with Reasoning Models: papers tagged with both rose from 9 in 2023 to 437 in 2026.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Reinforcement Learning papers

405 papers, page 5 of 9

201. ICML 2025LLMs Can Reason Faster Only If We Let Them
202. ICML 2025LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models
203. ICML 2025Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planning
204. ICML 2025Log-Sum-Exponential Estimator for Off-Policy Evaluation and Learning
205. ICML 2025Logarithmic Regret for Online KL-Regularized Reinforcement Learning
206. ICML 2025LOGO --- Long cOntext aliGnment via efficient preference Optimization
207. ICML 2025M³HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality
208. ICML 2025MARGE: Improving Math Reasoning with Guided Exploration
209. ICML 2025Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer
210. ICML 2025Maximum Entropy Reinforcement Learning with Diffusion Policy
211. ICML 2025Maximum Total Correlation Reinforcement Learning
212. ICML 2025MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning
213. ICML 2025Meta-Black-Box-Optimization through Offline Q-function Learning
214. ICML 2025Meta-Reinforcement Learning with Adaptation from Human Feedback via Preference-Order-Preserving Task Embedding
215. ICML 2025Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback
216. ICML 2025Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn
217. ICML 2025Model Immunization from a Condition Number Perspective
218. ICML 2025Model-Based Exploration in Monitored Markov Decision Processes
219. ICML 2025MODULI: Unlocking Preference Generalization via Diffusion Models for Offline Multi-Objective Reinforcement Learning
220. ICML 2025MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking
221. ICML 2025Monte Carlo Tree Diffusion for System 2 Planning
222. ICML 2025MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment
223. ICML 2025Multi-objective Linear Reinforcement Learning with Lexicographic Rewards
224. ICML 2025Multi-Session Budget Optimization for Forward Auction-based Federated Learning
225. ICML 2025Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning
226. ICML 2025Multi-Timescale Dynamics Model Bayesian Optimization for Plasma Stabilization in Tokamaks
227. ICML 2025Multi-Turn Code Generation Through Single-Step Rewards
228. ICML 2025Multiple-policy Evaluation via Density Estimation
229. ICML 2025Navigating the Social Welfare Frontier: Portfolios for Multi-objective Reinforcement Learning
230. ICML 2025NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations
231. ICML 2025Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback
232. ICML 2025Near-Optimal Sample Complexity for MDPs via Anchoring
233. ICML 2025Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning
234. ICML 2025Neurosymbolic World Models for Sequential Decision Making
235. ICML 2025Novelty Detection in Reinforcement Learning with World Models
236. ICML 2025O-MAPL: Offline Multi-agent Preference Learning
237. ICML 2025Of Mice and Machines: A Comparison of Learning Between Real World Mice and RL Agents
238. ICML 2025Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation
239. ICML 2025Off-Policy Evaluation under Nonignorable Missing Data
240. ICML 2025Offline Opponent Modeling with Truncated Q-driven Instant Policy Refinement
241. ICML 2025Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation
242. ICML 2025Omni-Angle Assault: An Invisible and Powerful Physical Adversarial Attack on Face Recognition
243. ICML 2025On Teacher Hacking in Language Model Distillation
244. ICML 2025On the Adversarial Robustness of Multi-Kernel Clustering
245. ICML 2025On the Guidance of Flow Matching
246. ICML 2025On the Robustness of Reward Models for Language Model Alignment
247. ICML 2025Online Episodic Convex Reinforcement Learning
248. ICML 2025Online Laplacian-Based Representation Learning in Reinforcement Learning
249. ICML 2025Online Learning in Risk Sensitive constrained MDP
250. ICML 2025Online Pre-Training for Offline-to-Online Reinforcement Learning

FAQ

How many Reinforcement Learning papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

6,885 in total: 1,070 in 2023, 1,190 in 2024, 1,640 in 2025, 2,985 in 2026.

How many Reinforcement Learning papers are at NeurIPS 2026?

NeurIPS 2026 has 760 Reinforcement Learning papers, versus 784 the year before.

How many Reinforcement Learning papers are at ICLR 2026?

ICLR 2026 has 911 Reinforcement Learning papers, versus 379 the year before.

How many Reinforcement Learning papers are at ICML 2026?

ICML 2026 has 1,021 Reinforcement Learning papers, versus 405 the year before.

How many Reinforcement Learning papers are at CVPR 2026?

CVPR 2026 has 293 Reinforcement Learning papers, versus 72 the year before.

Which conference publishes the most Reinforcement Learning papers?

NeurIPS, with 2,494 papers from 2023 to 2026.