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 2,079 篇，第 7 / 42 页
- ICML 2026Experience is the Best Teacher: Motivating Effective Exploration in Reinforcement Learning for LLMs
- ICML 2026Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic–Procedural Memory
- ICML 2026Exploration Hacking: Can LLMs Learn to Resist RL Training?
- ICML 2026ExpWeaver: LLM Agents Learn from Experience via Latent RAG
- ICML 2026FAB: A First-Order AB-based Gradient Algorithm for Distributed Bilevel Optimization over Time-Varying Directed Graphs
- ICML 2026FactGuard: Agentic Video Misinformation Detection via Reinforcement Learning
- ICML 2026Factored Causal Representation Learning for Robust Reward Modeling in RLHF
- ICML 2026Factored Value Functions for Graph-Based Multi-Agent Reinforcement Learning
- ICML 2026FAIL: Flow Matching Adversarial Imitation Learning for Image Generation
- ICML 2026Faithful Mobile GUI Agents with Guided Advantage Estimator
- ICML 2026Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning
- ICML 2026Fast Mixing Steady-State Control in Markov Decision Processes
- ICML 2026Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholding
- ICML 2026FIDIA: Function-Informed Sequence Design via Inference-Aligned Policy Optimization
- ICML 2026Find, Fix, Reason: Context Repair for Video Reasoning
- ICML 2026Finite-time Convergence Analysis of Actor-Critic with Evolving Reward
- ICML 2026Finite-Width Neural Tangent Kernels from Feynman Diagrams
- ICML 2026FIRE: Learning to Navigate and Act on Real-World Files via Stateful Reinforcement Learning
- ICML 2026FLAC: Maximum Entropy RL via Kinetic Energy Regularized Bridge Matching
- ICML 2026FocalPolicy: Frequency-Optimized Chunking and Locally Anchored Flow Matching for Coherent Visuomotor Policy
- ICML 2026Focus-Then-Contact: Speeding Up Robotic Contact-Rich Task Learning with Affordance-Guided Real-World Residual Reinforcement Learning
- ICML 2026FOCUS: Forcing In-Context Object Localization through Visual Support Constraints and Policy Optimization
- ICML 2026ForceForget: Reinforcement Concept Removal for Enhancing Safety in Text-to-Image Models
- ICML 2026ForesightKV: Optimizing KV Cache Eviction for Reasoning Models by Learning Long-Term Contribution
- ICML 2026Formalizing Learning from Language Feedback with Provable Guarantees
- ICML 2026FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation
- ICML 2026FourTune: Towards Fully 4-Bit Efficient Post-Training for Diffusion Models
- ICML 2026Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning
- ICML 2026Frictional Q-Learning
- ICML 2026From Absolute to Relative: Rethinking Reward Shaping in Group-Based Reinforcement Learning
- ICML 2026From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models
- ICML 2026From Generative to Episodic: Sample-Efficient Replicable Reinforcement Learning
- ICML 2026From Guessing to Placeholding: A Cost-Theoretic Framework for Uncertainty-Aware Code Completion
- ICML 2026From Interactions to Principles: Experience-Driven Self-Distillation for Evolving LLM Agents
- ICML 2026From Lyapunov Analysis to Algorithm Design in two-sided PL Minimax Optimization
- ICML 2026From Optimization to Generalization under Heavy-Tailed Data: The Role of Gradient Clipping
- ICML 2026From Outcomes to Actions: Leveraging Hindsight for Long-Horizon Language Agent Training
- ICML 2026From Parameters to Feature Space: Task Arithmetic for Backdoor Mitigation in Model Merging
- ICML 2026From Player to Master: Enhancing Test-Time Learning of LLM Agents via Reinforcement Learning over Memory
- ICML 2026From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs
- ICML 2026From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning
- ICML 2026From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning
- ICML 2026From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning
- ICML 2026From Shortcuts to Reasoning: Robust Post-Training of Theory of Mind with Reinforcement Learning
- ICML 2026From Static Constraints to Dynamic Adaptation: Sample-Level Constraint Relaxation for Offline-to-Online Reinforcement Learning
- ICML 2026From Teacher Pathways to Invariant Manifolds: Consensus Subspace Distillation for TSFMs
- ICML 2026Functional building blocks of neural networks: from network motifs to collective dynamics
- ICML 2026G$^2$RPO: Geometric GRPO; Escaping LLM's Reasoning Rut to Break Accuracy--Entropy Trade-off
- ICML 2026GameVerse: Can Vision-Language Models Learn from Video-based Reflection?
- ICML 2026GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
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。