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 1,640 篇，第 23 / 33 页
- NeurIPS 2025Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions
- NeurIPS 2025GenPO: Generative Diffusion Models Meet On-Policy Reinforcement Learning
- NeurIPS 2025GLID$^2$E: A Gradient-Free Lightweight Fine-tune Approach for Discrete Biological Sequence Design
- NeurIPS 2025Global Convergence for Average Reward Constrained MDPs with Primal-Dual Actor Critic Algorithm
- NeurIPS 2025Globally Optimal Policy Gradient Algorithms for Reinforcement Learning with PID Control Policies
- NeurIPS 2025GoalLadder: Incremental Goal Discovery with Vision-Language Models
- NeurIPS 2025GPO: Learning from Critical Steps to Improve LLM Reasoning
- NeurIPS 2025Graph Neural Network Based Action Ranking for Planning
- NeurIPS 2025GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining
- NeurIPS 2025Greedy Sampling Is Provably Efficient For RLHF
- NeurIPS 2025GRIT: Teaching MLLMs to Think with Images
- NeurIPS 2025Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Data
- NeurIPS 2025Grounded Reinforcement Learning for Visual Reasoning
- NeurIPS 2025Group-in-Group Policy Optimization for LLM Agent Training
- NeurIPS 2025GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
- NeurIPS 2025GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning
- NeurIPS 2025GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents
- NeurIPS 2025GUI-Rise: Structured Reasoning and History Summarization for GUI Navigation
- NeurIPS 2025Guiding Cross-Modal Representations with MLLM Priors via Preference Alignment
- NeurIPS 2025GVPO: Group Variance Policy Optimization for Large Language Model Post-Training
- NeurIPS 2025Gymnasium: A Standard Interface for Reinforcement Learning Environments
- NeurIPS 2025Hadamax Encoding: Elevating Performance in Model-Free Atari
- NeurIPS 2025HCRMP: An LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving
- NeurIPS 2025HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages
- NeurIPS 2025Hephaestus: Mixture Generative Modeling with Energy Guidance for Large-scale QoS Degradation
- NeurIPS 2025Heterogeneous Graph Transformers for Simultaneous Mobile Multi-Robot Task Allocation and Scheduling under Temporal Constraints
- NeurIPS 2025Hierarchical Optimization via LLM-Guided Objective Evolution for Mobility-on-Demand Systems
- NeurIPS 2025Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation
- NeurIPS 2025High-Dimensional Calibration from Swap Regret
- NeurIPS 2025High-order Interactions Modeling for Interpretable Multi-Agent Q-Learning
- NeurIPS 2025HMARL-CBF – Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems
- NeurIPS 2025Horizon Reduction Makes RL Scalable
- NeurIPS 2025How Ensembles of Distilled Policies Improve Generalisation in Reinforcement Learning
- NeurIPS 2025How Far Are We from Optimal Reasoning Efficiency?
- NeurIPS 2025How to Train Your LLM Web Agent: A Statistical Diagnosis
- NeurIPS 2025Human-assisted Robotic Policy Refinement via Action Preference Optimization
- NeurIPS 2025Hybrid Latent Reasoning via Reinforcement Learning
- NeurIPS 2025HyperMARL: Adaptive Hypernetworks for Multi-Agent RL
- NeurIPS 2025Hyperphantasia: A Benchmark for Evaluating the Mental Visualization Capabilities of Multimodal LLMs
- NeurIPS 2025HYPRL: Reinforcement Learning of Control Policies for Hyperproperties
- NeurIPS 2025Imagine Beyond ! Distributionally Robust Autoencoding for State Space Coverage in Online Reinforcement Learning
- NeurIPS 2025Imagined Autocurricula
- NeurIPS 2025Imitation Beyond Expectation Using Pluralistic Stochastic Dominance
- NeurIPS 2025Imitation Learning with Temporal Logic Constraints
- NeurIPS 2025Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections
- NeurIPS 2025Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay
- NeurIPS 2025Improving LLM General Preference Alignment via Optimistic Online Mirror Descent
- NeurIPS 2025Improving Model-Based Reinforcement Learning by Converging to Flatter Minima
- NeurIPS 2025Improving Monte Carlo Tree Search for Symbolic Regression
- NeurIPS 2025Improving planning and MBRL with temporally-extended actions
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。