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 58 / 60 页
- NeurIPS 2026STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability
- NeurIPS 2026StateTree: Enhancing Long-term Dialogue Reasoning via Reinforcement Learning
- NeurIPS 2026Statistical Complexity of Soft Bellman Residual Minimization
- NeurIPS 2026Steer2Edit: From Activation Steering to Component-Level Editing
- NeurIPS 2026Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces
- NeurIPS 2026Step-wise Rubric Rewards for LLM Reasoning
- NeurIPS 2026Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning
- NeurIPS 2026StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
- NeurIPS 2026Strategic Decision Focused Learning
- NeurIPS 2026Strengthening LLMs for Tabular Prediction with Structural Priors
- NeurIPS 2026STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning
- NeurIPS 2026Structural Entropy Optimized Communication for Multi-Agent Reinforcement Learning
- NeurIPS 2026Structure-aware Reinforcement Learning for Protein Directed Evolution
- NeurIPS 2026Subprocess-Constrained Markov Decision Processes
- NeurIPS 2026Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RL
- NeurIPS 2026SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents
- NeurIPS 2026Synsema: Syntax-Guided Learning of Semantically Valid Programs
- NeurIPS 2026Tail-Risk-Aware Stackelberg Learning
- NeurIPS 2026Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation-Level Enforcement
- NeurIPS 2026Taming the Curses of Multiagency in Robust Markov Games with Large State Space through Linear Function Approximation
- NeurIPS 2026TANGO: RNA Topology and Geometry Co-Design
- NeurIPS 2026TARP: Trace-Anchored Regularization Prior for Retaining Stepwise Reasoning
- NeurIPS 2026Teach-to-Reason: Competition-Guided Reasoning with a Self-Improving Teacher
- NeurIPS 2026TEMPO: Temporal Enforcement via Mode-Separated Policy Optimization for Trustworthy LLM Backtesting
- NeurIPS 2026Temporal Consistency Improves Generalization in Contextual Offline Meta Reinforcement Learning
- NeurIPS 2026Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning
- NeurIPS 2026Temporal Selective Exploration for Reinforcement Learning-Guided Continuous-Discrete Flow Matching in 3D Molecular Design
- NeurIPS 2026Test-time Multi-agent Coordination by Decomposed Value Gradient Flow
- NeurIPS 2026Test-time Risk Adaptation with Mixture of Agents
- NeurIPS 2026TGPO: Temporal Grounded Policy Optimization for Signal Temporal Logic Tasks
- NeurIPS 2026TGPO: Trace-Guided Policy Optimization for Robot Task Planning via Verifiable Subgoal Generation
- NeurIPS 2026TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs
- NeurIPS 2026The Benefits of Temporal Correlations: SGD Efficiently Learns k-Juntas from Random Walks
- NeurIPS 2026The Capability Frontier of GRPO
- NeurIPS 2026The Cost of Mismatch: Noise Amplification in Zeroth-Order Reinforcement Learning
- NeurIPS 2026The Era of Agentic Organization: Learning to Organize with Language Models
- NeurIPS 2026The Horizon Threshold in Cooperative Multi-Agent Reward-Free Exploration
- NeurIPS 2026The Illusion of Diversity: Aligning LLM Exploration via Effective Entropy
- NeurIPS 2026The Laplacian Keyboard: Beyond the Linear Span
- NeurIPS 2026The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes
- NeurIPS 2026The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning
- NeurIPS 2026The Post-Training Dilemma: Why We Should Rethink the Sequential SFT-RL Paradigm
- NeurIPS 2026The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models
- NeurIPS 2026The Reciprocity Gradient
- NeurIPS 2026The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL.
- NeurIPS 2026The Sample Complexity of Multiple Change Point Identification under Bandit Feedback
- NeurIPS 2026The Sampling Complexity of Condorcet Winner Identification in Dueling Bandits
- NeurIPS 2026The Surprising Effectiveness of Deleting Weights in LLM Reasoning and Adaptation
- NeurIPS 2026The Type Theory of Stationary MDPs: Rare Events and Uncertainty Quantification
- NeurIPS 2026Theoretical Limits of Language Model Alignment
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。