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 2,079 篇，第 1 / 42 页

1. ICML 2026“very likely” Means “uncertain”? How LLMs Diverge from Humans in Linguistic Uncertainty Quantification
2. ICML 2026$\text{DT}^\text{2}$: Decision-Targeted Digital Twins
3. ICML 2026$\textit{S}$-SPPO: Semantic-Calibrated Self-Play Preference Optimization
4. ICML 2026$\texttt{Multi}^2$: Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Interactive Environments
5. ICML 2026$f$-Divergence Regularized RLHF: Two Tales of Sampling and Unified Analyses
6. ICML 2026$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data
7. ICML 20263D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Understanding
8. ICML 2026A Generalist Pair-wise Progress Critic Model for Vision-Language-Action Robots
9. ICML 2026A KL-regularization framework for learning to plan with adaptive priors
10. ICML 2026A Regret Minimization Framework on Preference Learning in Large Language Models
11. ICML 2026A Solver-Free Training Method for Predict-then-Optimize
12. ICML 2026AC-ODM: Actor–Critic Online Data Mixing for Sample-Efficient LLM Pretraining
13. ICML 2026Accelerating Q-learning through Efficient Value-Sharing across Actions
14. ICML 2026Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning
15. ICML 2026Achieving Logarithmic Regret in KL-Regularized Zero-Sum Markov Games
16. ICML 2026ACTG-ARL: Differentially Private Conditional Text Generation with RL-Boosted Control
17. ICML 2026Action Manifold Smoothing: A Lipschitz Pathway Perspective on High-Dimensional Reinforcement Learning
18. ICML 2026Action-Sufficient Goal Representations
19. ICML 2026Active Attacks: Red-teaming LLMs via Adaptive Environments
20. ICML 2026Active Curriculum Refinement for Reinforcement Learning
21. ICML 2026Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language Models
22. ICML 2026Active Policy Optimization for Individualized Dosing via Gradient Variance Minimization
23. ICML 2026ACTIVE-o3 : Empowering MLLMs with Active Perception via Pure Reinforcement Learning
24. ICML 2026ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning
25. ICML 2026AdamO: A Collapse-Suppressed Optimizer for Offline RL
26. ICML 2026Adaptive Code Watermarking Through Reinforcement Learning
27. ICML 2026Adaptive Multi-Round Allocation with Stochastic Arrivals
28. ICML 2026Adaptive Policy Backbone via Shared Network
29. ICML 2026Adaptive Quasimetric Mapping : Principled Topological Abstraction for Robust Offline Goal-Conditioned Navigation
30. ICML 2026Adaptive Reinforcement Learning for Unobservable Random Delays
31. ICML 2026Adaptive Time Series Reasoning via Segment Selection
32. ICML 2026Addressing Semantic Blind Spots in Text-to-SQL via Component Pre-generation and AST Matching Rewards
33. ICML 2026Advancing LLM Reasoning with Natural Language and Numerical Feedback
34. ICML 2026Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation
35. ICML 2026Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models
36. ICML 2026Adversarial Dual On-Policy Distillation from Expressive Teacher
37. ICML 2026Adversarial Reinforcement Learning for Robust Diffusion Large Language Model Unlearning
38. ICML 2026AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning
39. ICML 2026Agent Learning via Early Experience
40. ICML 2026Agent-Omit: Adaptive Context Omission for Efficient LLM Agents
41. ICML 2026Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning
42. ICML 2026AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code Generation
43. ICML 2026Agentic Monte Carlo: Simulating Reinforcement Learning for Black-Box Agents
44. ICML 2026Alignment Risks from Capability-Seeking RL Training
45. ICML 2026Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases
46. ICML 2026Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion Models
47. ICML 2026AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in Unified Multimodal Models via Decompositional Verifiable Reward
48. ICML 2026AlphaRouter: Token-level Routing Between SLM and LLM with Reinforcement Learning and Tree Search
49. ICML 2026ALSO: Adversarial Online Strategy Optimization for Social Agents
50. ICML 2026Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training

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。