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 6 / 21 页
- ICML 2026Dreaming in Code for Curriculum Learning in Open-Ended Worlds
- ICML 2026DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization
- ICML 2026DRIVE: Best Data Scheduling Practices for Reinforcement Learning with Verifiable Reward in Competitive Code Generation
- ICML 2026DRIVE: Distributional and Retrieval-Augmented Bidding with Value Evaluation
- ICML 2026DRL-STAF: A Deep Reinforcement Learning Framework for State-Aware Forecasting of Complex Multivariate Hidden Markov Processes
- ICML 2026dTRPO : Trajectory Reduction in Policy Optimization of Diffusion Large Language Models
- ICML 2026DualCOIL: Offline Imitation Learning from Contrasting Demonstrations
- ICML 2026DyGRO-VLA: Cross-Task Scaling of Vision–Language–Action Models via Dynamic Grouped Residual Optimization
- ICML 2026Dynamic Optimizations of LLM Ensembles with Two-Stage Reinforcement Learning Agents
- ICML 2026Dynamic Programming for Epistemic Uncertainty in Markov Decision Processes
- ICML 2026Dynamics Are Learned, Not Told: Semi-Supervised Discovery of Latent Dynamics Geometries For Zero-Shot Policy Adaptation
- ICML 2026EAPO: Enhancing Policy Optimization with On-Demand Expert Assistance
- ICML 2026EARL: Towards a Unified Analysis-Guided Reinforcement Learning Framework for Egocentric Interaction Reasoning and Pixel Grounding
- ICML 2026ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretation
- ICML 2026ECHO: Entropy-Confidence Hybrid Optimization for Test-Time Reinforcement Learning
- ICML 2026EchoRL: Reinforcement Learning via Rollout Echoing
- ICML 2026EDCO: Dynamic Curriculum Orchestration for Domain-specific Large Language Model Fine-tuning
- ICML 2026EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment
- ICML 2026Effects of Structural Reward Shaping on Biophysical Properties in RL-Trained Plasmid Generators
- ICML 2026Efficient and Safe Molecular Assembly via Reinforcement Learning and Constraint Solving
- ICML 2026Efficient and Uncertainty-Aware Diffusion Framework for Offline-to-Online Reinforcement Learning
- ICML 2026Efficient Preference Poisoning Attack on Offline RLHF
- ICML 2026Efficient, Property-Aligned Fan-Out Retrieval via RL-Compiled Diffusion
- ICML 2026Efficiently Solving Discounted MDPs via Predictions with Unknown Prediction Errors
- ICML 2026Ego3S: Select, Strengthen, and Synchronize for Efficient Egocentric Reasoning
- ICML 2026Elign: Equivariant Diffusion Model Alignment from Foundational Machine Learned Force Fields
- ICML 2026Embedding-perturbed Exploration Preference Optimization for Flow Models
- ICML 2026Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying
- ICML 2026Emergent Communication Under Misinformation
- ICML 2026Enhancing Multi-Modal LLMs Reasoning via Difficulty-Aware Group Normalization
- ICML 2026Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization
- ICML 2026Entropy-Aware On-Policy Distillation of Language Models
- ICML 2026Episodic Memory-Guided Controllable Experience Synthesis for Reinforcement Learning
- ICML 2026Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoning
- ICML 2026Error Amplification Limits ANN-to-SNN Conversion in Continuous Control
- ICML 2026Escaping the Likelihood Trap: Geometric Diversity Optimization for Long-Form Image Captioning
- ICML 2026Escaping the Mode: Multi-Answer Reinforcement Learning in LMs
- ICML 2026Escaping the Verifier: Learning to Reason via Demonstrations
- ICML 2026Estimation of Treatment Effects Under Nonstationarity via the Truncated Policy Gradient Estimator
- ICML 2026ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment
- ICML 2026Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability
- ICML 2026Evaluating Parameter Efficient Methods for RLVR
- ICML 2026Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
- ICML 2026Evolution Strategies at the Hyperscale
- ICML 2026EVOLVING ROLLOUTS: Harnessing Historical Experience for Web Agent Evolution in Reinforcement Learning
- ICML 2026Exact Unlearning in Reinforcement Learning
- ICML 2026Expanding the Capabilities of Reinforcement Learning via Text Feedback
- ICML 2026Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling
- ICML 2026Expected Returns and Policy Inconsistency-Aware Offline Federated Deep Reinforcement Learning
- ICML 2026Experience Augmented Policy Optimization for LLM Reasoning
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。