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

760 papers, page 11 of 16

501. NeurIPS 2026Q-MMR: Off-Policy Evaluation via Recursive Reweighting and Moment Matching
502. NeurIPS 2026Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing
503. NeurIPS 2026QMaxCal: Path-Space Regularization for Open Quantum Control via Girsanov's Theorem
504. NeurIPS 2026Quantile Geometry Regularization for Distributional Reinforcement Learning
505. NeurIPS 2026Quantile-Coupled Flow Matching for Distributional Reinforcement Learning
506. NeurIPS 2026Quest: Training Frontier Deep Research Agents with Fully Synthetic Tasks
507. NeurIPS 2026Quotient-Categorical Representations for Bellman-Compatible Average-Reward Distributional Reinforcement Learning
508. NeurIPS 2026RAHF: Reward-Amplified Human Feedback for Closed-Loop Policy Fine-Tuning
509. NeurIPS 2026Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding
510. NeurIPS 2026Read It Back: Pretrained MLLMs Are Zero-shot Reward Models for Text-to-Image Generation
511. NeurIPS 2026Reason to Play: Behavioral and Brain Alignment Between Frontier LRMs and Human Game Learners
512. NeurIPS 2026Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck
513. NeurIPS 2026Reasoning Warm-up: Scaling Label-free RL via Verifiable Surrogate Rewards
514. NeurIPS 2026Reasoning with Sampling: Cutting at Decision Points
515. NeurIPS 2026RECAP: Looking Once Is Not Enough for Vision-Language Reasoning
516. NeurIPS 2026ReCon: Toward Balanced Learning under Inter-Context and Context-Memory Conflicts
517. NeurIPS 2026Reconciling Operational Energy Trilemma: A Heterogeneous Risk-Constrained MDP Framework with Residual Policy Learning
518. NeurIPS 2026Reconciling Safety and Performance via Dual-Expert Offline Imitation Learning
519. NeurIPS 2026Rectified Policy Rollouts with Hierarchical Expert Guidance for Neural Combinatorial Optimization
520. NeurIPS 2026ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving
521. NeurIPS 2026Reflective Prompted Policy Optimization: Trajectory-Grounded Revision and Salience Bias
522. NeurIPS 2026ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation
523. NeurIPS 2026Reinforcement Learning Agents Are Swimmers
524. NeurIPS 2026Reinforcement learning enhanced flow matching for reference-based tumor generation on unpaired CT images
525. NeurIPS 2026Reinforcement Learning for Code Optimization
526. NeurIPS 2026Reinforcement Learning for Diffusion LLMs with Entropy-Guided Step Selection and Stepwise Advantages
527. NeurIPS 2026Reinforcement Learning for Exponential Utility: Algorithms and Convergence in Discounted MDPs
528. NeurIPS 2026Reinforcement Learning for View-Adaptive Distillation in 3D Gaussian Compression
529. NeurIPS 2026Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batching
530. NeurIPS 2026Reinforcement Learning with Verifiable Physics: Post-training LLMs for PDE Solver Generation
531. NeurIPS 2026Reinforcing Multimodal Reasoning Against Visual Degradation
532. NeurIPS 2026Replay-buffer engineering for noise-robust quantum circuit optimization
533. NeurIPS 2026Representation Learning Enables Scalable Multitask Deep Reinforcement Learning
534. NeurIPS 2026Residual Expertise Is Not Decision Value
535. NeurIPS 2026Rethinking "RL Generalizes, SFT Memorizes": The Role of SFT Data
536. NeurIPS 2026Rethinking Learning from Label Proportions via Moment Matching
537. NeurIPS 2026Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting
538. NeurIPS 2026Rethinking Ratio-Based Trust Regions for Policy Optimization in Multi-Agent Reinforcement Learning
539. NeurIPS 2026RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments
540. NeurIPS 2026Reverse to Advance: Teleoperation-Cost Effective Hard Policy Learning from Reversed Easy Tasks
541. NeurIPS 2026REVERSE: Reinforcing Evidence Verification and Search for Agentic Image Geolocation
542. NeurIPS 2026Revisiting Value Iteration: Unified Analysis of Discounted and Average-Reward Cases
543. NeurIPS 2026Reward Hacking in Rubric-Based Reinforcement Learning
544. NeurIPS 2026Reward Inflation: A Healthy Stimulus for Reinforcement Learning
545. NeurIPS 2026Reward Is Not a Universal Interface for Generative Reinforcement Learning
546. NeurIPS 2026Reward Shaping to Improve Language Model Query Generation
547. NeurIPS 2026Reward-Conditioned Reinforcement Learning
548. NeurIPS 2026Reward-Estimated Hypergradient for Bilevel Reinforcement Learning with Black-Box Follower
549. NeurIPS 2026RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with LLMs
550. NeurIPS 2026Rich Insights from Cheap Signals: Efficient Evaluations via Tensor Factorization

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.