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 1,827 篇，第 5 / 37 页
- ICLR 2026DriveAgent-R1: Advancing VLM-based Autonomous Driving with Active Perception and Hybrid Thinking
- ICLR 2026DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization
- ICLR 2026Dual Goal Representations
- ICLR 2026Dual-Objective Reinforcement Learning with Novel Hamilton-Jacobi-Bellman Formulations
- ICLR 2026Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts
- ICLR 2026DUET: Optimizing LLM Training Data Mixtures via Noisy Feedback from Unseen, Downstream Evaluation Tasks
- ICLR 2026DuPO: Enabling Reliable Self-Verification via Dual Preference Optimization
- ICLR 2026DVLA-RL: Dual-Level Vision–Language Alignment with Reinforcement Learning Gating for Few-Shot Learning
- ICLR 2026Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
- ICLR 2026Dynamic Speculative Agent Planning
- ICLR 2026Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models
- ICLR 2026Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning
- ICLR 2026EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling
- ICLR 2026EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget
- ICLR 2026Efficient and Sharp Off-Policy Learning under Unobserved Confounding
- ICLR 2026Efficient Estimation of Kernel Surrogate Models for Task Attribution
- ICLR 2026Efficient Morphology–Control Co-Design via Stackelberg PPO under Non-Differentiable Leader–Follower Interfaces
- ICLR 2026Efficient Offline Reinforcement Learning via Peer-Influenced Constraint
- ICLR 2026Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data
- ICLR 2026EGG-SR: Embedding Symbolic Equivalence into Symbolic Regression via Equality Graph
- ICLR 2026Ego-Foresight: Self-supervised Learning of Agent-Aware Representations for Improved RL
- ICLR 2026Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance
- ICLR 2026ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL
- ICLR 2026Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
- ICLR 2026Emergence of Spatial Representation in an Actor-Critic Agent with Hippocampus-Inspired Sequence Generator
- ICLR 2026Emergent Dexterity Via Diverse Resets and Large-Scale Reinforcement Learning
- ICLR 2026Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
- ICLR 2026EmotionThinker: Prosody-Aware Reinforcement Learning for Explainable Speech Emotion Reasoning
- ICLR 2026Empowering LLM Tool Invocation with Tool-call Reward Model
- ICLR 2026Empowering Multi-Robot Cooperation via Sequential World Models
- ICLR 2026Empowering Small VLMs to Think with Dynamic Memorization and Exploration
- ICLR 2026ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction
- ICLR 2026Enforcing Axioms for AI Alignment under Loss-Based Rules
- ICLR 2026Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search
- ICLR 2026Enhancing Geometric Perception in VLMs via Translator-Guided Reinforcement Learning
- ICLR 2026Enhancing Language Model Reasoning with Structured Multi-Level Modeling
- ICLR 2026Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs
- ICLR 2026Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints
- ICLR 2026Entropy-preserving reinforcement learning
- ICLR 2026Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs
- ICLR 2026ERGO: Efficient High-Resolution Visual Understanding for Vision-Language Models
- ICLR 2026Escaping Policy Contraction: Contraction-Aware PPO (CaPPO) for Stable Language Model Fine-Tuning
- ICLR 2026EUBRL: Epistemic Uncertainty Directed Bayesian Reinforcement Learning
- ICLR 2026Evaluating and Improving Cultural Awareness of Reward Models for LLM Alignment
- ICLR 2026Evaluating GFlowNet from partial episodes for stable and flexible policy-based training
- ICLR 2026EVLP: Learning Unified Embodied Vision-Language Planner with Reinforced Supervised Fine-Tuning
- ICLR 2026EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems
- ICLR 2026ExGRPO: Learning to Reason from Prior Successes
- ICLR 2026Exo-Plore: Exploring Exoskeleton Control Space through Human-aligned Simulation
- ICLR 2026Expanding Reasoning Potential in Foundation Model by Learning Diverse Chains of Thought Patterns
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。