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 2,985 篇，第 9 / 60 页
- ICLR 2026CE-Nav: Flow-Guided Reinforcement Refinement for Cross-Embodiment Local Navigation
- ICLR 2026CellDuality: Unlocking Biological Reasoning in LLMs with Self-Supervised RLVR
- ICLR 2026Chain-of-Context Learning: Dynamic Constraint Understanding for Multi-Task VRPs
- ICLR 2026Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training
- ICLR 2026Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns
- ICLR 2026CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives
- ICLR 2026Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models
- ICLR 2026CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control
- ICLR 2026COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferences
- ICLR 2026CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards
- ICLR 2026Combinatorial Rising Bandits
- ICLR 2026CompassNav: Steering From Path Imitation to Decision Understanding In Navigation
- ICLR 2026Composition of Memory Experts for Diffusion World Models
- ICLR 2026Composition-Grounded Instruction Synthesis for Visual Reasoning
- ICLR 2026ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents
- ICLR 2026Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models
- ICLR 2026Conformal Robustness Control: A New Strategy for Robust Decision
- ICLR 2026Conformalized Decision Risk Assessment
- ICLR 2026Consis-GCPO: Consistency-Preserving Group Causal Preference Optimization for Vision Customization
- ICLR 2026Consolidating Reinforcement Learning for Multimodal Discrete Diffusion Models
- ICLR 2026Contact-guided Real2Sim from Monocular Video with Planar Scene Primitives
- ICLR 2026ContextIF: Enhancing Instruction-Following through Context Reward
- ICLR 2026Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model
- ICLR 2026Continuous-Time Value Iteration for Multi-Agent Reinforcement Learning
- ICLR 2026Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning
- ICLR 2026Controllable Logical Hypothesis Generation for Abductive Reasoning in Knowledge Graphs
- ICLR 2026Convergence of an actor-critic gradient flow for entropy regularised MDPs in general spaces
- ICLR 2026ConvRec-R1: Training LLM-based Conversational Recommender Systems with Reinforcement Learning
- ICLR 2026CoPRS: Learning Positional Prior from Chain-of-Thought for Reasoning Segmentation
- ICLR 2026Correlated Policy Optimization in Multi-Agent Subteams
- ICLR 2026Count Counts: Motivating Exploration in LLM Reasoning with Count-based Intrinsic Rewards
- ICLR 2026Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning
- ICLR 2026Cross-Domain Policy Optimization via Bellman Consistency and Hybrid Critics
- ICLR 2026Cross-Embodied Co-Design for Dexterous Hands
- ICLR 2026Cross-Embodiment Offline Reinforcement Learning for Heterogeneous Robot Datasets
- ICLR 2026CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning
- ICLR 2026CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs
- ICLR 2026Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning
- ICLR 2026Dancing in Chains: Strategic Persuasion in Academic Rebuttal via Theory of Mind
- ICLR 2026DARE-bench: Evaluating Modeling and Instruction Fidelity of LLMs in Data Science
- ICLR 2026Data-to-Energy Stochastic Dynamics
- ICLR 2026DaVinci: Reinforcing Visual-Structural Syntax in MLLMs for Generalized Scientific Diagram Parsing
- ICLR 2026DEAS: DEtached value learning with Action Sequence for Scalable Offline RL
- ICLR 2026Decision Aggregation under Quantal Response
- ICLR 2026Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner
- ICLR 2026Decomposing Extrapolative Problem Solving: Spatial Transfer and Length Scaling with Map Worlds
- ICLR 2026Deconstructing Positional Information: From Attention Logits to Training Biases
- ICLR 2026Decoupled Q-Chunking
- ICLR 2026Deep SPI: Safe Policy Improvement via World Models
- ICLR 2026DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains
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。