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 6,885 篇，第 78 / 138 页

3851. NeurIPS 2025A multiscale analysis of mean-field transformers in the moderate interaction regime
3852. NeurIPS 2025A Novel General Framework for Sharp Lower Bounds in Succinct Stochastic Bandits
3853. NeurIPS 2025A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning
3854. NeurIPS 2025A Principled Path to Fitted Distributional Evaluation
3855. NeurIPS 2025A Provable Approach for End-to-End Safe Reinforcement Learning
3856. NeurIPS 2025A Reinforcement Learning-based Bidding Strategy for Data Consumers in Auction-based Federated Learning
3857. NeurIPS 2025A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search
3858. NeurIPS 2025A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning
3859. NeurIPS 2025A Temporal Difference Method for Stochastic Continuous Dynamics
3860. NeurIPS 2025A Theory for Worst-Case vs. Average-Case Guarantees for LLMs
3861. NeurIPS 2025A Unifying View of Linear Function Approximation in Off-Policy RL Through Matrix Splitting and Preconditioning
3862. NeurIPS 2025Absolute Zero: Reinforced Self-play Reasoning with Zero Data
3863. NeurIPS 2025Accelerating RL for LLM Reasoning with Optimal Advantage Regression
3864. NeurIPS 2025Accelerating Visual-Policy Learning through Parallel Differentiable Simulation
3865. NeurIPS 2025AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning
3866. NeurIPS 2025Achieving $\tilde{\mathcal{O}}(1/N)$ Optimality Gap in Restless Bandits through Gaussian Approximation
3867. NeurIPS 2025Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
3868. NeurIPS 2025Act to See, See to Act: Diffusion-Driven Perception-Action Interplay for Adaptive Policies
3869. NeurIPS 2025Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models
3870. NeurIPS 2025Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models
3871. NeurIPS 2025ActiveVOO: Value of Observation Guided Active Knowledge Acquisition for Open-World Embodied Lifted Regression Planning
3872. NeurIPS 2025Actor-Free Continuous Control via Structurally Maximizable Q-Functions
3873. NeurIPS 2025Adaptable Safe Policy Learning from Multi-task Data with Constraint Prioritized Decision Transformer
3874. NeurIPS 2025Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback
3875. NeurIPS 2025Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization
3876. NeurIPS 2025Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning
3877. NeurIPS 2025Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models
3878. NeurIPS 2025Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning
3879. NeurIPS 2025Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural Networks
3880. NeurIPS 2025Adaptive Variance Inflation in Thompson Sampling: Efficiency, Safety, Robustness, and Beyond
3881. NeurIPS 2025Adaptively Coordinating with Novel Partners via Learned Latent Strategies
3882. NeurIPS 2025AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking
3883. NeurIPS 2025ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning
3884. NeurIPS 2025Adversarial Diffusion for Robust Reinforcement Learning
3885. NeurIPS 2025Adversarial Locomotion and Motion Imitation for Humanoid Policy Learning
3886. NeurIPS 2025AegisGuard: RL-Guided Adapter Tuning for TEE-Based Efficient & Secure On-Device Inference
3887. NeurIPS 2025Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization
3888. NeurIPS 2025Agentic RL Scaling Law: Spontaneous Code Execution for Mathematical Problem Solving
3889. NeurIPS 2025Align-DA: Align Score-based Atmospheric Data Assimilation with Multiple Preferences
3890. NeurIPS 2025Aligning Transformers with Continuous Feedback via Energy Rank Alignment
3891. NeurIPS 2025ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisition
3892. NeurIPS 2025AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws
3893. NeurIPS 2025AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction
3894. NeurIPS 2025Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning
3895. NeurIPS 2025Angles Don’t Lie: Unlocking Training‑Efficient RL Through the Model’s Own Signals
3896. NeurIPS 2025Approximating Shapley Explanations in Reinforcement Learning
3897. NeurIPS 2025AREAL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning
3898. NeurIPS 2025ARIA: Training Language Agents with Intention-driven Reward Aggregation
3899. NeurIPS 2025Ask a Strong LLM Judge when Your Reward Model is Uncertain
3900. NeurIPS 2025Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards

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。