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 2,985 篇，第 59 / 60 页

2901. NeurIPS 2026There are Levels to It: Red Teaming LLMs with Hierarchical Reinforcement Learning
2902. NeurIPS 2026Thinking with Images as Continuous Policy: Numerical Visual Chain-of-Thought
2903. NeurIPS 2026ThinkSafe: Self-Generated Safety Alignment for Reasoning Models
2904. NeurIPS 2026TIGER: Bridging the Multimodal Reasoning-Access Gap via Modality Counterfactuals
2905. NeurIPS 2026Tool Verification for Test-Time Reinforcement Learning
2906. NeurIPS 2026ToolSearcher: Optimizing Tool Selection at Scale via Reinforcement Learning
2907. NeurIPS 2026Topic-Aware Contextual Cascading Bandits
2908. NeurIPS 2026TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing
2909. NeurIPS 2026ToS: Tree-of-Skill Reinforcement Learning driven by Behavior Tree for Long-Horizon Manipulation
2910. NeurIPS 2026Toward Cognitive Supersensing in Multimodal Large Language Models
2911. NeurIPS 2026Toward Embodied World Agents via Embodied-Planning Dataset and Interactive World Models
2912. NeurIPS 2026Toward Executable Multi-framework Front-end Code Generation with Self-Correction
2913. NeurIPS 2026Toward Online Robust Zero-Sum Markov Games with Function Approximation
2914. NeurIPS 2026Towards Convergence of PPO: An Approximate Descent Approach
2915. NeurIPS 2026Towards Differentially Private Reinforcement Learning with General Function Approximation
2916. NeurIPS 2026Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents
2917. NeurIPS 2026Towards Optimal Pre-training Data Mixtures for Empowering Reinforcement Learning in LLMs
2918. NeurIPS 2026TPRL: Adaptive Visual Token Pruning in LVLMs via Language-Guided Reinforcement Learning
2919. NeurIPS 2026Train at the Moving Edge: Rollout-Efficient RL for Large Reasoning Models
2920. NeurIPS 2026Train the Agent, Not the Expert: Learning to Harness Heterogeneous Experts for Multi-Turn Visual Reasoning
2921. NeurIPS 2026Training Agent to Scale Inference-Time Reasoning
2922. NeurIPS 2026Training Generalizable Collaborative Agents via Strategic Risk Aversion
2923. NeurIPS 2026Training on Documents About Monitoring Leads to CoT Obfuscation
2924. NeurIPS 2026Training-Induced Escape from Token Clustering in a Mean-Field Formulation of Transformers
2925. NeurIPS 2026Trajectory-Consistent Diffusion Policies for Offline Reinforcement Learning
2926. NeurIPS 2026Transfer Learning of Linear Regression with Multiple Pretrained Models: Benefiting from More Pretrained Models via Overparameterization Debiasing
2927. NeurIPS 2026Treat Bias as Noise: Training Bias-Robust LLM Reasoning via Reinforcement Learning
2928. NeurIPS 2026Tree Training: Efficient LLM Training on Tree-Structured Trajectories
2929. NeurIPS 2026Trust Guided Decision Transformer
2930. NeurIPS 2026Trust Region Q Adjoint Matching
2931. NeurIPS 2026TrustFlow: Adaptive Trust Calibration for Language Model Guided Reinforcement Learning
2932. NeurIPS 2026Tuning the Tuner
2933. NeurIPS 2026Ultra-DPO: Reimagining LLM Alignment as a Semi-Supervised Task
2934. NeurIPS 2026Uncertainty-Aware Listwise Reinforcement Fine-Tuning for Fine-Grained Visual Classification
2935. NeurIPS 2026Uncertainty-Guided Reward Labeling for Reinforcement Learning under Limited Feedback
2936. NeurIPS 2026Underlying Functional Structure of Reinforcement Learning
2937. NeurIPS 2026Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning
2938. NeurIPS 2026Unlearning Diffusion Policies via Relative Fisher Forgetting
2939. NeurIPS 2026Unleashing the Power of Intrinsic-Entropy-Driven Exploration for Off-Policy Generative RL
2940. NeurIPS 2026Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation
2941. NeurIPS 2026Value-Priced Uncertainty: A Family of PPO-Compatible Exploration Bonuses
2942. NeurIPS 2026Value-Rectified Distillation for Flow-based Offline Reinforcement Learning
2943. NeurIPS 2026Variance-Adaptive Optimal Algorithm for Reinforcement Learning with MNL Function Approximation
2944. NeurIPS 2026Variance-Averse n-Step Offline Reinforcement Learning for Sparse Long-Horizon Environments
2945. NeurIPS 2026Variational Consequence-Driven Offline Reinforcement Learning
2946. NeurIPS 2026VC-OPD: Visual Counterfactual On-Policy Distillation for Grounded Vision-Language Reasoning
2947. NeurIPS 2026Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization
2948. NeurIPS 2026VESPO: Variational Sequence-level Soft Policy Optimization for Off-Policy LLM Training
2949. NeurIPS 2026VI-Bench: Benchmarking Prompt Inversion from AIGC Videos
2950. NeurIPS 2026VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction

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。