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 57 / 60 页
- NeurIPS 2026SAMPPO: Structure-Aware Mirror Proximal Policy Optimization
- NeurIPS 2026Scalable Minimal-Change Learning for Controllable Image Editing
- NeurIPS 2026Scalable Multi-Agent Contrastive Reinforcement Learning
- NeurIPS 2026SceneFactory: GPU-Accelerated Multi-Agent Driving Simulation with Physics-Based Vehicle Dynamics
- NeurIPS 2026Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models
- NeurIPS 2026SD-Search: Hindsight Self-Distillation for Search-Augmented Reasoning
- NeurIPS 2026SEAR: Sample Efficient Action Chunking Reinforcement Learning
- NeurIPS 2026Seeing but Not Detecting: Privacy-Preserving Scene Text Attack via Hybrid Adversarial Policy Learning
- NeurIPS 2026Selective Off-Policy Reference Tuning with Plan Guidance
- NeurIPS 2026Self-Calibrated GUI Reward Model via Inverse Dynamic Modeling
- NeurIPS 2026Self-Correction as Transition Geometry: Internalizing Reasoning via Lifted State Policy Optimization
- NeurIPS 2026Self-Distilled RLVR
- NeurIPS 2026Self-Evolution Reasoner: Continuous Optimization via Policy-Intrinsic Exploration and Exploitation
- NeurIPS 2026Self-Evolving Agents Should Build Internal and External Models of the World
- NeurIPS 2026Self-Improvement Imitation with Biologically Guided Search for Protein Design Under Oracle Budgets
- NeurIPS 2026Self-Supervised On-Policy Reinforcement Learning via Contrastive Proximal Policy Optimisation
- NeurIPS 2026SelfCritic-VLA: Language as Intrinsic Critic for Vision Language Action Models in Autonomous Driving
- NeurIPS 2026Serialization Tax in Shared-Latent Exchangeable Decisions
- NeurIPS 2026SETA: Scaling Environments for Terminal Agents
- NeurIPS 2026SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
- NeurIPS 2026Shared Modular Recurrence in Contextual MDPs for Universal Morphology Control
- NeurIPS 2026Sharper Guarantees for Misspecified Kernelized Bandit Optimization
- NeurIPS 2026Signal-Adaptive Trust Regions for Gradient-Free Optimization of Recurrent Spiking Neural Networks
- NeurIPS 2026Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators
- NeurIPS 2026Simulation-aided Reinforcement Learning with Control Variates
- NeurIPS 2026SIRAS: Sibling-Relative Advantage Shaping for Reinforcement Learning from Verifiable Rewards
- NeurIPS 2026Skill-Coupled Policy Optimization with Calibrated Group-Wise Advantage Estimation
- NeurIPS 2026Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
- NeurIPS 2026SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles
- NeurIPS 2026SLOPE: Optimistic Potential Landscape Shaping for Model-based Reinforcement Learning
- NeurIPS 2026Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots
- NeurIPS 2026SOC-ICNN: From Polyhedral to Conic Geometry for Learning Convex Surrogate Functions
- NeurIPS 2026Soft Forward-Backward Representations for Zero-shot Reinforcement Learning with General Utilities
- NeurIPS 2026SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning
- NeurIPS 2026Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests
- NeurIPS 2026SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing
- NeurIPS 2026SPECS: Faster Test-Time Scaling through Speculative Drafts and Dynamic Switching
- NeurIPS 2026Spectral Geometry of Attention: From Information Routing to Uncertainty
- NeurIPS 2026Spectral Representations for Provably Robust Offline Meta-Reinforcement Learning from Bagged Rewards
- NeurIPS 2026Spiking neural network initialization for scale-invariant maximization of entropy
- NeurIPS 2026Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation
- NeurIPS 2026Split-RL: Local Conflict Resolution in Reinforcement Learning
- NeurIPS 2026SPRING: Solver-guided Process Rewards for Novel Logical Reasoning Steps Generation
- NeurIPS 2026SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment
- NeurIPS 2026SRL-MPC: Shape-Aware Reinforcement Learned Model Predictive Control
- NeurIPS 2026Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR
- NeurIPS 2026Stabilizing Policy Optimization via Logits Convexity
- NeurIPS 2026Stable and Granular Policy Optimization for Generative Recommendation
- NeurIPS 2026StainNFT: Curriculum-Gated Multi-Reward Post-Training for Pathology-Faithful Virtual Staining
- NeurIPS 2026STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens
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。