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 2,494 篇，第 2 / 50 页
- NeurIPS 2026BalCapRL : A Balanced Framework for RL-Based MLLM Image Captioning
- NeurIPS 2026Bayesian Preference Learning for Test-Time Steerable Reward Models
- NeurIPS 2026BECON: Belief-Conditioned Constrained Multi-Objective Reinforcement Learning under Drifting Preferences and Budgets
- NeurIPS 2026Behaving Better, Thinking Worse: Sycophancy Across Post-Training Stages
- NeurIPS 2026Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback
- NeurIPS 2026Behavior-Discriminative Reward Shaping for Reward-Robust Reinforcement Learning
- NeurIPS 2026Behavioral Foundation Models for Quality Diversity
- NeurIPS 2026Bellman Residual Minimization for Control: Geometry, Stationarity, and Convergence
- NeurIPS 2026Benchmarking and Optimizing Multimodal Structured Generation: The OracleGraph Dataset and PRISM Framework
- NeurIPS 2026Benign Reinforcement Learning Can Amplify Latent Backdoors
- NeurIPS 2026Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns
- NeurIPS 2026Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents
- NeurIPS 2026Beyond Prediction: Steering VLM Agents with Retrospective World Modeling
- NeurIPS 2026Beyond SFT-to-RL: Pre-alignment via Black-box On-policy Distillation for Multimodal RL
- NeurIPS 2026Beyond Success Rates: Trainability and Extractability in Offline GCRL
- NeurIPS 2026Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Image Generation
- NeurIPS 2026Beyond Training Time, Test-Time Coordination is Essential for Cooperative MARL
- NeurIPS 2026BiasTrojan: LLM Judgers Are Easily Distorted by Few Hundreds of Contrastive Biased Training Data
- NeurIPS 2026Bilevel Optimization of Synthetic Trajectories for Multi-Turn LLM Fine-Tuning
- NeurIPS 2026BioMicroAgents: A Co-evolutionary Multi-Agent Framework for High-Fidelity Biomicroscopy Imaging
- NeurIPS 2026BIRD-RL: Scaling Agentic Reinforcement Learning over Stateful Data-Centric Environments
- NeurIPS 2026BlendCast: Teaching Vision-Language Model to Anticipate Member Skill in Weather Ensembles
- NeurIPS 2026BlenderFORGE: Framework for Optimizing Reactive 3D-Graphics Editing Ability of MLLMs
- NeurIPS 2026Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models
- NeurIPS 2026Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- NeurIPS 2026Boosting LLM Reasoning via Human-Inspired Reward Shaping
- NeurIPS 2026Boosting Off-Policy RLVR with Data-Centric Replay
- NeurIPS 2026Bootstrapped Bipartite Actor-Critic for Diffusion RL
- NeurIPS 2026Breaking the Bias Barrier in Concave Multi-Objective Reinforcement Learning
- NeurIPS 2026Breaking the Grid: Distance-Guided Reinforcement Learning in Large Discrete Action Spaces
- NeurIPS 2026Breaking the Second Barrier: Sub-Second Timestamped Omni-Modal Captioning
- NeurIPS 2026Bridging Risk Approximation Gaps in Model Predictive Task Sampling via In-Context Modeling
- NeurIPS 2026Bridging Textual Profiles and Latent User Embeddings for Personalization
- NeurIPS 2026BSO: Safety Alignment Is Density Ratio Matching
- NeurIPS 2026Budgeting Discretion: Theory and Evidence on Street-Level Decision-Making
- NeurIPS 2026C2G-BENCH: A Cyber-Physical Evaluation Benchmark for Hierarchical Reinforcement Learning in Grid-Interactive Hyperscale Data Centers
- NeurIPS 2026CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating
- NeurIPS 2026CAFE: Causally-Guided Automated Feature Engineering with Multi-Agent Reinforcement Learning
- NeurIPS 2026Calibrated Safe Policy Improvement for Continuous Offline Reinforcement Learning
- NeurIPS 2026Calibrated Target Noise Recovers Curvature from the Gradients
- NeurIPS 2026Can Folding Models Tell Binders from Bluffers? Evidence from POISK: The Patent-Derived Antibody Dataset
- NeurIPS 2026CARD: Internalizing Expert Critique into Reinforcement Learning for Deep Search
- NeurIPS 2026CasePlay: Self-Play Reinforcement Learning from Case Reports for Medical Reasoning
- NeurIPS 2026Causal-Geo: Neuro-Symbolic Spatial Grounding for Situated Agent Planning
- NeurIPS 2026Certified Policy Optimisation for Nested Causal Bandits via PAC-Bayes Risk
- NeurIPS 2026CHAIN: Continual Heterogeneous Cooperation with Information Bottleneck for Multi-Agent Reinforcement Learning
- NeurIPS 2026CI4A: Semantic Component Interfaces for Agents Empowering Web Automation
- NeurIPS 2026CIG: Exploration via Conditional Information Gain
- NeurIPS 2026Clarification as Supervision: Reinforcement Learning for Vision-Language Interfaces
- NeurIPS 2026Clean-Label Poisoning for Gradient-Boosted Decision Trees
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。