强化学习论文趋势 2023–2026

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。

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 405 篇，第 8 / 9 页

351. ICML 2025Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry
352. ICML 2025Speeding up Policy Simulation in Supply Chain RL
353. ICML 2025Square$\chi$PO: Differentially Private and Robust $\chi^2$-Preference Optimization in Offline Direct Alignment
354. ICML 2025Stable Offline Value Function Learning with Bisimulation-based Representations
355. ICML 2025Stay Hungry, Keep Learning: Sustainable Plasticity for Deep Reinforcement Learning
356. ICML 2025Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning
357. ICML 2025Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Design
358. ICML 2025Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence
359. ICML 2025Stochastic Encodings for Active Feature Acquisition
360. ICML 2025STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving
361. ICML 2025Strategic Planning: A Top-Down Approach to Option Generation
362. ICML 2025Subgoal-Guided Policy Heuristic Search with Learned Subgoals
363. ICML 2025Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales
364. ICML 2025T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling
365. ICML 2025Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner
366. ICML 2025Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks
367. ICML 2025Teaching Language Models to Critique via Reinforcement Learning
368. ICML 2025Temporal Difference Flows
369. ICML 2025Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning
370. ICML 2025Test-Time Adaptation for Online Vision-Language Navigation with Feedback-based Reinforcement Learning
371. ICML 2025Test-Time Adaptation with Binary Feedback
372. ICML 2025Test-time Adapted Reinforcement Learning with Action Entropy Regularization
373. ICML 2025TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization
374. ICML 2025The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning
375. ICML 2025The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking
376. ICML 2025The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks
377. ICML 2025The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes
378. ICML 2025The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
379. ICML 2025The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability
380. ICML 2025The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data
381. ICML 2025Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization
382. ICML 2025Think Twice, Act Once: A Co-Evolution Framework of LLM and RL for Large-Scale Decision Making
383. ICML 2025Time-Aware World Model for Adaptive Prediction and Control
384. ICML 2025Towards Cost-Effective Reward Guided Text Generation
385. ICML 2025Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning
386. ICML 2025Towards Theoretical Understanding of Sequential Decision Making with Preference Feedback
387. ICML 2025Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings
388. ICML 2025Training Flexible Models of Genetic Variant Effects from Functional Annotations using Accelerated Linear Algebra
389. ICML 2025Transfer Q-Learning with Composite MDP Structures
390. ICML 2025Trust-Region Twisted Policy Improvement
391. ICML 2025TtBA: Two-third Bridge Approach for Decision-Based Adversarial Attack
392. ICML 2025Universal Approximation Theorem of Deep Q-Networks
393. ICML 2025Unraveling the Interplay between Carryover Effects and Reward Autocorrelations in Switchback Experiments
394. ICML 2025Unveiling Markov heads in Pretrained Language Models for Offline Reinforcement Learning
395. ICML 2025Value-Based Deep RL Scales Predictably
396. ICML 2025Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach
397. ICML 2025VinePPO: Refining Credit Assignment in RL Training of LLMs
398. ICML 2025Vintix: Action Model via In-Context Reinforcement Learning
399. ICML 2025Wait-Less Offline Tuning and Re-solving for Online Decision Making
400. ICML 2025Wasserstein Policy Optimization

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。