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 48 / 60 页
- NeurIPS 2026Correct, Route, Calibrate: Efficient Preference Optimization from Noisy, Heterogeneous Human Feedback
- NeurIPS 2026Correctable Fork Tokens: Verifier-Anchored Selective Credit Assignment for Tool-Integrated RLVR
- NeurIPS 2026Cost-Aware Learning
- NeurIPS 2026CoT-Guard: Small Models for Strong Monitoring
- NeurIPS 2026Counterfactual Distillation: Internalizing Reflective Experience into LLM Agent
- NeurIPS 2026Counterfactual Rollout Replay: Forkable Environments as Free Process Rewards for Software Engineering Agents
- NeurIPS 2026Coupling-Aware Reinforcement Learning for Co-Evolving Graph Games
- NeurIPS 2026CPA: Efficient and Stable FP4 RL Training via Cross-Precision Alignment
- NeurIPS 2026CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies
- NeurIPS 2026Credit Assignment with Resets in Language Model Reasoning
- NeurIPS 2026Cross-Question Reliable Reinforcement Learning
- NeurIPS 2026CS-DICE: Offline Reinforcement Learning with Coherent Occupancy Regularization
- NeurIPS 2026CURe: Conservative Unlearning with Soft-Gating Regularization for Offline Reinforcement Learning
- NeurIPS 2026CURE: Coupled User-Grouped Reinforcement Learning for Cross-Domain Recommendation with Non-Overlapping Users
- NeurIPS 2026Curriculum proof repair with learned counterexamples
- NeurIPS 2026CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning
- NeurIPS 2026CyCLeGen: Cycle-Consistent Layout Prediction and Image Generation
- NeurIPS 2026D-VLA: A High-Concurrency Distributed Asynchronous RL Framework for Vision-Language-Action Models
- NeurIPS 2026DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models
- NeurIPS 2026DACE RL for Compute Efficient Reinforcement Learning in Small Model Reasoning
- NeurIPS 2026DaCe-DT: Data-Centric Offline Multi-Task Reinforcement Learning via Adaptive Prompts and Trajectory Correction for Heterogeneous Tasks
- NeurIPS 2026DARLING: Detection Augmented Reinforcement Learning with Non-Stationary Guarantees
- NeurIPS 2026DASM: Dynamic Autoregressive Subgraph Mining via Two-Stage Policy Alignment
- NeurIPS 2026DDACOM: Dual-Decoupled Adaptive Communication for Multi-Agent Reinforcement Learning under Dynamic Networks
- NeurIPS 2026Deadline-Constrained Dynamic Workflow Scheduling Can be Cast as a Representation Learning Problem
- NeurIPS 2026Decentralized Multi-Goal Multi-Agent Pathfinding with Spatial Prior and Neighbor Intent Prediction
- NeurIPS 2026Decision Focused Scenario Learning for Contextual Stochastic Programming
- NeurIPS 2026Decision-Focused Learning in MDPs: An Occupancy Measure Approach
- NeurIPS 2026Decomposed Graded Verifier for Generative World Modeling
- NeurIPS 2026Decomposing the modulation of interactions between neuronal populations
- NeurIPS 2026Decoupling Conversational Dynamics in Full-Duplex Spoken Models through Reinforcement Learning
- NeurIPS 2026Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration
- NeurIPS 2026Deep Double Q-learning
- NeurIPS 2026Deep Heteroskedastic Regression: Post-Hoc Variance Estimation from Latent Representations
- NeurIPS 2026DeFlow: Decoupling Behavior-Prior Modeling and Value Maximization for Offline Policy Extraction
- NeurIPS 2026DeFlowCritic: Dense Latent Reward Alignment for Text-to-Image Flow Matching Models
- NeurIPS 2026Delightful Distributed Policy Gradient
- NeurIPS 2026Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Model
- NeurIPS 2026Designing Reinforcement Learning for Diffusion Models: A Unified Path-Space View
- NeurIPS 2026Dexterous Skill Discovery via Topology-Aware Wasserstein Dependency
- NeurIPS 2026DGRAF: Observation-Quality-Aware Reinforcement Learning for Dynamic Reconfigurable Batteries
- NeurIPS 2026Differentiable Belief-based Opponent Shaping
- NeurIPS 2026Diffusion fine-tuning with Rewarded Moment Matching Distillation
- NeurIPS 2026Diffusion Subgoal Planning for Long-Horizon Offline Goal-Conditioned Reinforcement Learning
- NeurIPS 2026Diffusion-State Policy Optimization for Masked Diffusion Language Models
- NeurIPS 2026DiReCL: Learning Differentiable Reward Code with Inverse Reinforcement Learning
- NeurIPS 2026DISCOVER: Online Variance-Guided Data Discovery for Budgeted Multimodal GRPO
- NeurIPS 2026Disentangling the Good From the Bad: Quantization-Induced Flips Are Not Random
- NeurIPS 2026Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving
- NeurIPS 2026Distilling LLM Feedback for Lean Theorem Proving
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。