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 21 of 60

1001. ICLR 2026Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
1002. ICLR 2026Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs
1003. ICLR 2026Self-Aligned Reward: Towards Effective and Efficient Reasoners
1004. ICLR 2026Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking
1005. ICLR 2026SELF-HARMONY: LEARNING TO HARMONIZE SELF-SUPERVISION AND SELF-PLAY IN TEST-TIME REINFORCEMENT LEARNING
1006. ICLR 2026Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement Learning
1007. ICLR 2026Self-Improving Vision-Language-Action Models with Data Generation via Residual RL
1008. ICLR 2026Self-Rewarding Vision-Language Model via Reasoning Decomposition and Multi-Reward Policy Optimization
1009. ICLR 2026SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks
1010. ICLR 2026Semantic-aware Wasserstein Policy Regularization for Large Language Model Alignment
1011. ICLR 2026SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration
1012. ICLR 2026Shift-Tolerant Allocation via Black-Litterman Using Conditional Diffusion Estimates
1013. ICLR 2026Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning
1014. ICLR 2026Shortcut Diffusion Training with Cumulative Consistency Loss: An Optimal Control View
1015. ICLR 2026Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle
1016. ICLR 2026SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
1017. ICLR 2026SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
1018. ICLR 2026Simplicial Embeddings Improve Sample Efficiency in Actor–Critic Agents
1019. ICLR 2026Single-stream Policy Optimization
1020. ICLR 2026SK2Decompile: LLM-based Two-Phase Binary Decompilation from Skeleton to Skin
1021. ICLR 2026SketchThinker-R1: Towards Efficient Sketch-Style Reasoning in Large Multimodal Models
1022. ICLR 2026Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning
1023. ICLR 2026SkillFactory: Self-Distillation for Learning Cognitive Behaviors
1024. ICLR 2026Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning
1025. ICLR 2026SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG
1026. ICLR 2026Smarter Not Harder: Generative Process Evaluation with Intrinsic-Signal Driving and Ability‑Adaptive Reward Shaping
1027. ICLR 2026SocialJax: An Evaluation Suite for Multi-agent Reinforcement Learning in Sequential Social Dilemmas
1028. ICLR 2026Soft Tokens, Hard Truths
1029. ICLR 2026Solving Football by Exploiting Equilibrium Structure of 2p0s Differential Games with One-Sided Information
1030. ICLR 2026Solving General-Utility Markov Decision Processes in the Single-Trial Regime with Online Planning
1031. ICLR 2026Solving Parameter-Robust Avoid Problems with Unknown Feasibility using Reinforcement Learning
1032. ICLR 2026SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward
1033. ICLR 2026SPACeR: Self-Play Anchoring with Centralized Reference Models
1034. ICLR 2026Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs
1035. ICLR 2026SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
1036. ICLR 2026SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start
1037. ICLR 2026Spectral Bellman Method: Unifying Representation and Exploration in RL
1038. ICLR 2026SpeechJudge: Towards Human-Level Judgment for Speech Naturalness
1039. ICLR 2026SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models
1040. ICLR 2026SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models
1041. ICLR 2026SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
1042. ICLR 2026SportR: A Benchmark for Multimodal Large Language Model Reasoning in Sports
1043. ICLR 2026Spotlight on Token Perception for Multimodal Reinforcement Learning
1044. ICLR 2026Squeeze the Soaked Sponge: Efficient Off-policy RFT for Large Language Model
1045. ICLR 2026SR-Scientist: Scientific Equation Discovery With Agentic AI
1046. ICLR 2026SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning
1047. ICLR 2026SSVPO: Effective Step-Level Credit Assignment for RL Training of Language Models
1048. ICLR 2026Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping
1049. ICLR 2026Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning
1050. ICLR 2026Stackelberg Coupling of Online Representation Learning and 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.