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 14 / 37 页
- ICLR 2026Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models
- ICLR 2026Reward Is Enough: LLMs Are In-Context Reinforcement Learners
- ICLR 2026Reward Model Routing in Alignment
- ICLR 2026RewardEval: Advancing Reward Model Evaluation
- ICLR 2026Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language Models
- ICLR 2026RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning
- ICLR 2026RFS: Reinforcement learning with Residual flow steering for dexterous manipulation
- ICLR 2026RIDER: 3D RNA Inverse Design with Reinforcement Learning-Guided Diffusion
- ICLR 2026Risk-Sensitive Agent Compositions
- ICLR 2026Risk-Sensitive Reinforcement Learning for Alleviating Exploration Dilemmas in Large Language Models
- ICLR 2026RiskPO: Risk-based Policy Optimization with Verifiable Reward for LLM Post-Training
- ICLR 2026RL for Reasoning by Adaptively Revealing Rationales
- ICLR 2026RL makes MLLMs see better than SFT
- ICLR 2026RL of Thoughts: Navigating LLM Reasoning with Inference-time Reinforcement Learning
- ICLR 2026RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs
- ICLR 2026RL's Razor: Why Online Reinforcement Learning Forgets Less
- ICLR 2026RLAP-CLIP: Continual Multimodal Learning with Prototype Adaptation and Difficulty-Aware Routing
- ICLR 2026RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards
- ICLR 2026RLP: Reinforcement as a Pretraining Objective
- ICLR 2026RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents
- ICLR 2026RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents
- ICLR 2026RM-R1: Reward Modeling as Reasoning
- ICLR 2026Robust Adaptive Multi-Step Predictive Shielding
- ICLR 2026Robust Decision-Making with Partially Calibrated Forecasters
- ICLR 2026Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation
- ICLR 2026Robust Optimization for Mitigating Reward Hacking with Correlated Proxies
- ICLR 2026Robust Preference Optimization: Aligning Language Models with Noisy Preference Feedback
- ICLR 2026Robustness in the Face of Partial Identifiability in Reward Learning
- ICLR 2026ROSETTA: Constructing Code-Based Reward from Unconstrained Language Preference
- ICLR 2026Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
- ICLR 2026RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling
- ICLR 2026SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling
- ICLR 2026SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without Training
- ICLR 2026Safe Continuous-time Multi-Agent Reinforcement Learning via Epigraph Form
- ICLR 2026Safe Exploration via Policy Priors
- ICLR 2026SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety
- ICLR 2026SafeMPO: Constrained Reinforcement Learning with Probabilistic Incremental Improvement
- ICLR 2026Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense
- ICLR 2026SAM-Veteran: An MLLM-Based Human-like SAM Agent for Reasoning Segmentation
- ICLR 2026Sample Efficient Offline RL via T-Symmetry Enforced Latent State-Stitching
- ICLR 2026Sample Lottery: Unsupervised Discovery of Critical Instances for LLM Reasoning
- ICLR 2026Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning
- ICLR 2026Sample-efficient and Scalable Exploration in Continuous-Time RL
- ICLR 2026Sample-Efficient Distributionally Robust Multi-Agent Reinforcement Learning via Online Interaction
- ICLR 2026Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning
- ICLR 2026Scalable Exploration for High-Dimensional Continuous Control via Value-Guided Flow
- ICLR 2026Scalable In-Context Q-Learning
- ICLR 2026Scalable Offline Model-Based RL with Action Chunks
- ICLR 2026Scaling Agent Learning via Experience Synthesis
- ICLR 2026Scaling Goal-conditioned Reinforcement Learning with Multistep Quasimetric Distances
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。