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

2,079 papers, page 21 of 42

1001. ICML 2026What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-Zoom
1002. ICML 2026What Makes Value Learning Efficient in Residual Reinforcement Learning?
1003. ICML 2026What Reward Structure Enables Efficient Sparse-Reward RL? A Proof-of-Concept with Policy-Aware Matrix Completion
1004. ICML 2026What You Think is What You See: Driving Exploration in VLM Agents via Visual-Linguistic Curiosity
1005. ICML 2026When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPs
1006. ICML 2026When Does Predictive Inverse Dynamics Outperform Behavior Cloning?
1007. ICML 2026When RL Meets Adaptive Speculative Training: A Unified Training-Serving System
1008. ICML 2026When Simple Problems Wear Complex Costumes: Improving Efficiency in LRM's Adaptive Reasoning
1009. ICML 2026When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning
1010. ICML 2026Which Heads Matter for Reasoning? RL-Guided KV Cache Compression
1011. ICML 2026Why Dedicated Critics: Eliminating Target Drift in Multi-Constraint RL
1012. ICML 2026Why Linear Recurrent Memory Works in Partially Observable Reinforcement Learning
1013. ICML 2026Why Tree-Style Branching Matters for Thought Advantage Estimation in GRPO
1014. ICML 2026World Models in Pieces: Structural Certification of General Agents
1015. ICML 2026World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
1016. ICML 2026WorldCompass: Reinforcement Learning for Long-Horizon World Models
1017. ICML 2026WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning
1018. ICML 2026XRPO: Pushing the Limits of GRPO with Targeted Exploration and Exploitation
1019. ICML 2026You Can Learn Tokenization End-to-End with Reinforcement Learning
1020. ICML 2026Zero-Shot Off-Policy Learning
1021. ICML 2026Zero-source LLM Hallucination Detection with Human-like Criteria Probing
1022. ICML 2025A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs
1023. ICML 2025A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control
1024. ICML 2025A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
1025. ICML 2025A Mixed-Curvature based Pre-training Paradigm for Multi-Task Vehicle Routing Solver
1026. ICML 2025A Model of Place Field Reorganization During Reward Maximization
1027. ICML 2025A Multi-Region Brain Model to Elucidate the Role of Hippocampus in Spatially Embedded Decision-Making
1028. ICML 2025A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous Systems
1029. ICML 2025A Reduction Framework for Distributionally Robust Reinforcement Learning under Average Reward
1030. ICML 2025A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents
1031. ICML 2025A Sharper Global Convergence Analysis for Average Reward Reinforcement Learning via an Actor-Critic Approach
1032. ICML 2025A Theoretical Justification for Asymmetric Actor-Critic Algorithms
1033. ICML 2025A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization
1034. ICML 2025A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO
1035. ICML 2025Accelerating Quantum Reinforcement Learning with a Quantum Natural Policy Gradient Based Approach
1036. ICML 2025Accurate and Efficient World Modeling with Masked Latent Transformers
1037. ICML 2025Action-Constrained Imitation Learning
1038. ICML 2025Action-Dependent Optimality-Preserving Reward Shaping
1039. ICML 2025Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss
1040. ICML 2025Active Fine-Tuning of Multi-Task Policies
1041. ICML 2025Active Reward Modeling: Adaptive Preference Labeling for Large Language Model Alignment
1042. ICML 2025Actor-Critics Can Achieve Optimal Sample Efficiency
1043. ICML 2025Ad Hoc Teamwork via Offline Goal-Based Decision Transformers
1044. ICML 2025Ad-Hoc Human-AI Coordination Challenge
1045. ICML 2025Adaptive Exploration for Multi-Reward Multi-Policy Evaluation
1046. ICML 2025Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection
1047. ICML 2025ADDQ: Adaptive distributional double Q-learning
1048. ICML 2025AdvAgent: Controllable Blackbox Red-teaming on Web Agents
1049. ICML 2025Adversarial Inception Backdoor Attacks against Reinforcement Learning
1050. ICML 2025Agent-Centric Actor-Critic for Asynchronous Multi-Agent 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.