强化学习论文趋势 2023–2026

主要结论

• 强化学习论文从 2023 年的 1,070 篇增长到 2026 年的 2,985 篇，三年间扩大到约 2.8 倍。
• NeurIPS 是发强化学习论文最多的会议，2023–2026 年共 2,494 篇，占四个会议总量的 36%。
• 交叉方向里涨得最快的是推理模型：同时属于两个主题的论文从 2023 年的 9 篇增至 2026 年的 437 篇。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• 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

全部强化学习论文

共 784 篇，第 8 / 16 页

351. NeurIPS 2025Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs
352. NeurIPS 2025Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL
353. NeurIPS 2025Less is More: an Attention-free Sequence Prediction Modeling for Offline Embodied Learning
354. NeurIPS 2025Leveraging Conditional Dependence for Efficient World Model Denoising
355. NeurIPS 2025LILO: Learning to Reason at the Frontier of Learnability
356. NeurIPS 2025Linear Mixture Distributionally Robust Markov Decision Processes
357. NeurIPS 2025LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models
358. NeurIPS 2025Logic.py: Bridging the Gap between LLMs and Constraint Solvers
359. NeurIPS 2025Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automation
360. NeurIPS 2025LOPT: Learning Optimal Pigovian Tax in Sequential Social Dilemmas
361. NeurIPS 2025MACS: Multi-Agent Reinforcement Learning for Optimization of Crystal Structures
362. NeurIPS 2025MALinZero: Efficient Low-Dimensional Search for Mastering Complex Multi-Agent Planning
363. NeurIPS 2025Markov Persuasion Processes: Learning to Persuade From Scratch
364. NeurIPS 2025Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning
365. NeurIPS 2025Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning
366. NeurIPS 2025Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning
367. NeurIPS 2025Memory-Enhanced Neural Solvers for Routing Problems
368. NeurIPS 2025Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-Tuning
369. NeurIPS 2025Meta-learning how to Share Credit among Macro-Actions
370. NeurIPS 2025Meta-Learning Objectives for Preference Optimization
371. NeurIPS 2025Meta-World+: An Improved, Standardized, RL Benchmark
372. NeurIPS 2025MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box Optimization
373. NeurIPS 2025MetaKoopman: Bayesian Meta-Learning of Koopman Operators for Modeling Structured Dynamics under Distribution Shifts
374. NeurIPS 2025MiCo: Multi-image Contrast for Reinforcement Visual Reasoning
375. NeurIPS 2025Mind the Gap: Bridging Thought Leap for Improved Chain-of-Thought Tuning
376. NeurIPS 2025Mind the GAP! The Challenges of Scale in Pixel-based Deep Reinforcement Learning
377. NeurIPS 2025MindJourney: Test-Time Scaling with World Models for Spatial Reasoning
378. NeurIPS 2025MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO
379. NeurIPS 2025MisoDICE: Multi-Agent Imitation from Mixed-Quality Demonstrations
380. NeurIPS 2025Mitigating Reward Over-optimization in Direct Alignment Algorithms with Importance Sampling
381. NeurIPS 2025Mixing Expert Knowledge: Bring Human Thoughts Back To the Game of Go
382. NeurIPS 2025Mixture-of-Experts Meets In-Context Reinforcement Learning
383. NeurIPS 2025MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?
384. NeurIPS 2025MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering
385. NeurIPS 2025MMaDA: Multimodal Large Diffusion Language Models
386. NeurIPS 2025Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol
387. NeurIPS 2025Model-Based Policy Adaptation for Closed-Loop End-to-end Autonomous Driving
388. NeurIPS 2025Modelling the control of offline processing with reinforcement learning
389. NeurIPS 2025MonoLift: Learning 3D Manipulation Policies from Monocular RGB via Distillation
390. NeurIPS 2025MOSDT: Self-Distillation-Based Decision Transformer for Multi-Agent Offline Safe Reinforcement Learning
391. NeurIPS 2025MRO: Enhancing Reasoning in Diffusion Language Models via Multi-Reward Optimization
392. NeurIPS 2025MTL-KD: Multi-Task Learning Via Knowledge Distillation for Generalizable Neural Vehicle Routing Solver
393. NeurIPS 2025MTRec: Learning to Align with User Preferences via Mental Reward Models
394. NeurIPS 2025Multi-Agent Collaboration via Evolving Orchestration
395. NeurIPS 2025Multi-Agent Imitation by Learning and Sampling from Factorized Soft Q-Function
396. NeurIPS 2025Multi-agent Markov Entanglement
397. NeurIPS 2025Multi-Agent Reinforcement Learning with Communication-Constrained Priors
398. NeurIPS 2025Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach
399. NeurIPS 2025Multi-step Visual Reasoning with Visual Tokens Scaling and Verification
400. NeurIPS 2025Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP

常见问题

2023–2026 年四大会议一共有多少篇强化学习论文？

共 6,885 篇，按年份分别是 2023 年 1,070 篇、2024 年 1,190 篇、2025 年 1,640 篇、2026 年 2,985 篇。

NeurIPS 2026 有多少篇强化学习论文？

NeurIPS 2026 有 760 篇强化学习论文，上一届是 784 篇。

ICLR 2026 有多少篇强化学习论文？

ICLR 2026 有 911 篇强化学习论文，上一届是 379 篇。

ICML 2026 有多少篇强化学习论文？

ICML 2026 有 1,021 篇强化学习论文，上一届是 405 篇。

CVPR 2026 有多少篇强化学习论文？

CVPR 2026 有 293 篇强化学习论文，上一届是 72 篇。

哪个会议的强化学习论文最多？

NeurIPS，2023–2026 年共 2,494 篇。