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

2,985 papers, page 54 of 60

2651. NeurIPS 2026Neural Spectral Capacity: An Architectural Quantity from Network Specification Alone
2652. NeurIPS 2026Neuro-Inspired Inverse Learning for Planning and Control
2653. NeurIPS 2026Never Stop Learning: Test-Time Reinforcement Learning for Vision-Language-Action Models
2654. NeurIPS 2026NitroBox: Lightning-Fast Sandbox for Large-Scale RL Training
2655. NeurIPS 2026Noisy Data is Destructive to Reinforcement Learning with Verifiable Rewards
2656. NeurIPS 2026Non-Asymptotic Best Policy Identification Guarantees in Online Reinforcement Learning
2657. NeurIPS 2026Not All Tokens Should Be Treated Equally: Context Credits Reassignment
2658. NeurIPS 2026Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR
2659. NeurIPS 2026NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models
2660. NeurIPS 2026Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders
2661. NeurIPS 2026Objective-Aligned Amortized Inference for Offline Bayes-Adaptive MDP Model Learning
2662. NeurIPS 2026Off-policy Learning with Excursion Policies
2663. NeurIPS 2026Offline Constrained Reinforcement Learning under Partial Data Coverage
2664. NeurIPS 2026Offline Inverse Reinforcement Learning with Unified Diffusion Planning
2665. NeurIPS 2026Offline Materials Optimization with CliqueFlowmer
2666. NeurIPS 2026Offline Reinforcement Learning for Plasma Control in Nuclear Fusion: Codebase and Benchmark
2667. NeurIPS 2026OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models
2668. NeurIPS 2026On the Complexity of Discounted Robust MDPs with $L_p$ Uncertainty Sets
2669. NeurIPS 2026On the Complexity of Offline Reinforcement Learning with Q*-Approximation and Partial Coverage
2670. NeurIPS 2026On the Convergence of Success Conditioning for Policy Optimization
2671. NeurIPS 2026On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization
2672. NeurIPS 2026On the Origin of Algorithmic Progress in AI: Evidence from Language Model Pre-Training
2673. NeurIPS 2026On-Policy Counterfactual Influence
2674. NeurIPS 2026One for All: A Non-Linear Transformer can enable Cross-Domain Generalization for In-Context Reinforcement Learning
2675. NeurIPS 2026One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective
2676. NeurIPS 2026Online Decision-Focused Learning under Semi-Bandit Feedback
2677. NeurIPS 2026OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
2678. NeurIPS 2026OpenSearcher: Democratizing Deep Search through a Fully Offline Pipeline with Programmatic Verification
2679. NeurIPS 2026OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
2680. NeurIPS 2026Optimistic Q-value Adaptation for Offline-to-Online Reinforcement Learning
2681. NeurIPS 2026Optimizer-Induced Mode Connectivity: From AdamW to Muon
2682. NeurIPS 2026Optimizing Agent Tool-Use via Trajectory-based Insight Evolution
2683. NeurIPS 2026Optimizing Social Utility in Sequential Experiments
2684. NeurIPS 2026Ordered Policy Optimization
2685. NeurIPS 2026Outbidding and Outbluffing Elite Humans: Mastering Liar’s Poker via Self-Play and Reinforcement Learning
2686. NeurIPS 2026Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data
2687. NeurIPS 2026Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
2688. NeurIPS 2026PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents
2689. NeurIPS 2026PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control
2690. NeurIPS 2026Parallel Computation Algorithms and Convergence Guarantees for Mean-Field Langevin Dynamics
2691. NeurIPS 2026Parameter Exploration for RLVR via Variational Learning
2692. NeurIPS 2026ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning
2693. NeurIPS 2026PASSAGE: A Real-Terrain Benchmark for Trustworthy Constrained Path Planning
2694. NeurIPS 2026PatternBloom: Empowering Agentic RAG with Externalized RL-Distilled Graph Patterns
2695. NeurIPS 2026Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs
2696. NeurIPS 2026Personalized and Collaborative Online LQR via Thompson Sampling
2697. NeurIPS 2026Persuasive Prediction via Decision Calibration
2698. NeurIPS 2026Pessimistic Latent Task-aware Optimization for Robust Offline Meta-Reinforcement Learning
2699. NeurIPS 2026PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning
2700. NeurIPS 2026PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation

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.