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 1,021 篇，第 18 / 21 页

851. ICML 2026Stochastic Gradient Variational Inference with Price's Gradient Estimator from Bures-Wasserstein to Parameter Space
852. ICML 2026Stochastic Minimum-Cost Reach-Avoid Reinforcement Learning
853. ICML 2026Strat-Reasoner: Reinforcing Strategic Reasoning of LLMs in Multi-Agent Games
854. ICML 2026Stratified GRPO: Handling Structural Heterogeneity in Reinforcement Learning of LLM Search Agents
855. ICML 2026StructMAR: Structure-Aware Masked Autoregression for Explicit Layout Alignment in Text-to-Image Generation
856. ICML 2026Structure-Induced Information for Rerooting Levin Tree Search
857. ICML 2026Structured Expert Routing with Multi-View Task Priors for Offline Meta-Reinforcement Learning
858. ICML 2026Student-Centered Distillation Narrows the Agentic Gap Between Small and Large LLMs
859. ICML 2026Success-Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success
860. ICML 2026SuCo: Sufficiency-guided Continuous Adaptive Reasoning
861. ICML 2026SVL: Goal-Conditioned Reinforcement Learning as Survival Learning
862. ICML 2026SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents
863. ICML 2026SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale
864. ICML 2026T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning
865. ICML 2026TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning
866. ICML 2026Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learning
867. ICML 2026TACTIC: Task-Aware Sparse Coordination Graphs for Multi-Task Multi-agent Reinforcement Learning
868. ICML 2026Tailoring the Training: Difficulty-Aware Learning Strategy Allocation for Large Language Models
869. ICML 2026Taming Aleatoric Impulse in Off-Policy Reinforcement Learning
870. ICML 2026TAMPO: Task- and Model-Aware Automatic Prompt Optimization for Auto-Routing in LLM-based Systems
871. ICML 2026Target-Driven Policy Optimization for Sequential Counterfactual Outcome Control
872. ICML 2026Task-Aware Exploration via a Predictive Bisimulation Metric
873. ICML 2026TaskLoom: Weaving Knowledge Across Tasks in World Models
874. ICML 2026TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward
875. ICML 2026Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability
876. ICML 2026Temporal Difference Calibration in Sequential Tasks: Application to Vision-Language-Action Models
877. ICML 2026Temporal Difference Learning for Diffusion Models
878. ICML 2026Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future
879. ICML 2026Temporal-Aware Reasoning Optimization for Video Temporal Grounding
880. ICML 2026Test-Time Graph Search for Goal-Conditioned Reinforcement Learning
881. ICML 2026Test-time Offline Reinforcement Learning on Goal-related Experience
882. ICML 2026Test-Time Reinforcement Learning for Flow Matching
883. ICML 2026TexEditor: Structure-Preserving Text-Driven Texture Editing
884. ICML 2026Text Before Vision: Staged Knowledge Injection Matters for Agentic RLVR in Ultra-High-Resolution Remote Sensing Understanding
885. ICML 2026Text Generation as Continuous Latent Dynamics via Reinforcement Learning
886. ICML 2026TGPO: Efficient Policy Optimization through Sequence Anchor and Information Gating
887. ICML 2026The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning
888. ICML 2026The Axiomatic Value of Regularization in AI Alignment from Human Preferences
889. ICML 2026The Cost of Commitment in Option-Based Hierarchical RL
890. ICML 2026The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind
891. ICML 2026The Easy, the Hard, and the Learnable: Confidence and Difficulty-Adaptive Policy Optimization for LLM Reasoning
892. ICML 2026The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models
893. ICML 2026The Hidden Link between RLHF and Contrastive Learning
894. ICML 2026The Implicit Bias of Depth: From Neural Collapse to Softmax Codes
895. ICML 2026The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes
896. ICML 2026The Optimal Token Baseline: Variance Reduction for Long-Horizon LLM-RL
897. ICML 2026The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomy
898. ICML 2026The Role of Target Update Frequencies in Q-Learning
899. ICML 2026The Sign Estimator: Preference Modeling for LLM Alignment under Heterogeneity
900. ICML 2026The Surprising Difficulty of Search in Model-Based 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。