强化学习论文趋势 2023–2026
策略优化、离线 RL 与基于环境的决策学习
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 6,885 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 484 | 233 | 297 | 56 | 1,070 |
| 2024 | 466 | 304 | 356 | 64 | 1,190 |
| 2025 | 784 | 379 | 405 | 72 | 1,640 |
| 2026 | 760 | 911 | 1,021 | 293 | 2,985 |
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 1,021 篇，第 8 / 21 页
- ICML 2026GenAlign: Towards Unified Alignment Framework of MLLMs via Generative Reward Model
- ICML 2026GenCircuit-RL: Reinforcement Learning from Hierarchical Verification for Genetic Circuit Design
- ICML 2026Generative Online Reinforcement Learning
- ICML 2026GeoAlign: Geometric Rollout Curation for Robust LLM Reinforcement Learning
- ICML 2026Geometric Coherence Learning for Structuring Value Functions in Plain MDPs
- ICML 2026Geometric Control of Out-of-Distribution Shift in Safe Offline RL
- ICML 2026Geometry-Preserving Orthonormal Initialization for Low-Rank Adaptation in RLVR
- ICML 2026GIPO: Gaussian Importance Sampling Policy Optimization
- ICML 2026GLARE: Scalable Neuro-Symbolic Reward Shaping for LLM Agents via Group-Level Automata
- ICML 2026Global Policy-Space Response Oracles for Two-Player Zero-Sum Games
- ICML 2026Goal-Conditioned Agents that Learn Everything All at Once
- ICML 2026Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text
- ICML 2026Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning
- ICML 2026Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards
- ICML 2026Gradient-Aware Scheduling: Coupling Curriculum and Staleness for Async Reinforcement Learning
- ICML 2026Gradient-Free Approaches is a Key to an Efficient Interaction with Markovian Stochasticity
- ICML 2026GradientStabilizer: Fix the Norm, Not the Gradient
- ICML 2026Graph-GRPO: Training Graph Flow Models with Reinforcement Learning
- ICML 2026Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning
- ICML 2026GRASP: Graph Reasoning via Agentic Solving and Probing of LLMs
- ICML 2026Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logs
- ICML 2026Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization
- ICML 2026Group Distributionally Robust Optimization-Driven RL for LLM Reasoning
- ICML 2026GRPO is Secretly a Process Reward Model
- ICML 2026GRPO-based Cluster Decision Agent for Unknown-$\boldsymbol{K}$ Multi-view Clustering
- ICML 2026GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy
- ICML 2026GUI-Spotlight: Adaptive Iterative Focus Refinement for Enhanced GUI Visual Grounding
- ICML 2026GXPO: Group Cross-Lingual Relative Policy Optimization for Code Generation
- ICML 2026Hard labels sampled from sparse targets mislead rotation invariant algorithms
- ICML 2026Harmonized Dual Policy Improvement for Modelic Reinforcement Learning
- ICML 2026Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents
- ICML 2026HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling
- ICML 2026Hierarchical Decision Making with Structured Policies: A Principled Design via Inverse Optimization
- ICML 2026Hierarchical Goal Abstractions via Learned Subset Relations
- ICML 2026Hierarchical Reinforcement Learning for Sparse-Reward Search in Commutative Algebra
- ICML 2026Hierarchical Successor Representation for Robust Transfer
- ICML 2026HiMAP-Travel: Hierarchical Multi-Agent Planning for Long-Horizon Constrained Travel
- ICML 2026HiPER: Hierarchical Plan–Execute RL for Multi-Turn LLM Agents
- ICML 2026Hista and Numca: Estimate State Value Effectively for Large Language Model Reinforcement Learning
- ICML 2026HodgeFlow Policy Search by Topologically Dissecting Temporal-Difference Signals in Non-Markovian Environments
- ICML 2026HoloFair: Unified T2I Fairness Evaluation and Fair-GRPO Debiasing
- ICML 2026Holonomy Grid Codes for Generalisation Under Directed Actions
- ICML 2026How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs
- ICML 2026How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?
- ICML 2026How Reasoning Evolves from Post-Training Data: An Empirical Study Using Chess
- ICML 2026How RL Unlocks the Aha Moment in Geometric Interleaved Reasoning
- ICML 2026How RLHF Amplifies Sycophancy
- ICML 2026How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models
- ICML 2026HPS: Hyperspherical Parameter Sharing for Efficient Multi-Agent Reinforcement Learning
- ICML 2026HTAC: Hierarchical Task-Aware Composition for Continual Offline Reinforcement Learning
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查强化学习在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "reinforcement-learning"}
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。