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 2,079 篇，第 2 / 42 页

51. ICML 2026An Evidential Route to Asymptotic Bayes Optimality under Sparsity
52. ICML 2026Anchored Policy Optimization: Mitigating Exploration Collapse via Support-Constrained Rectification
53. ICML 2026Anchoring Self-Play for Code Repair
54. ICML 2026Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning
55. ICML 2026AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection
56. ICML 2026Approximation of Log-Partition Function in Policy Mirror Descent Induces Implicit Regularization for LLM Post-Training
57. ICML 2026Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning
58. ICML 2026AReaL-DTA: Dynamic Tree Attention for Efficient Reinforcement Learning of Large Language Models
59. ICML 2026ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
60. ICML 2026ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning
61. ICML 2026Artemis: Structured Visual Reasoning for Perception Policy Learning
62. ICML 2026ASAP: Exploiting the Satisficing Generalization Edge in Neural Combinatorial Optimization
63. ICML 2026Asking What Matters: Reward-Driven Clarification for Software Engineering Tasks
64. ICML 2026ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models
65. ICML 2026Asymmetric Prompt Weighting for Reinforcement Learning with Verifiable Rewards
66. ICML 2026AtomWorld: A Benchmark for Evaluating Spatial Reasoning in Large Language Models on Material Structures
67. ICML 2026Attention Illuminates LLM Reasoning: The Uncovered Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization
68. ICML 2026AuTAgent: A Reinforcement Learning Framework for Tool-Augmented Audio Reasoning
69. ICML 2026Auto-regressive In-context Demonstration Selection
70. ICML 2026Automata-Conditioned Cooperative Multi-Agent Reinforcement Learning
71. ICML 2026Autoregressive Direct Preference Optimization
72. ICML 2026Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction
73. ICML 2026AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning
74. ICML 2026B-Spar: Bayesian Sparse-Reward Modeling for RL-based Image Editing
75. ICML 2026Backjump-on-Graph: Empowering Large Language Models with Reinforced Retrospective Exploration for Agentic Knowledge Graph Reasoning
76. ICML 2026Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning
77. ICML 2026Balancing Plasticity and Stability with Fast and Slow Successor Features
78. ICML 2026BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning
79. ICML 2026Batched Contextual Reinforcement
80. ICML 2026Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning
81. ICML 2026Behavioral Mode Discovery for Fine-tuning Multimodal Generative Policies
82. ICML 2026Benchmarking and Improving Fine-Grained Text-to-Image Alignment via Paired Reinforcement Learning
83. ICML 2026Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis
84. ICML 2026Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork
85. ICML 2026Best-of-Both-Worlds for Heavy-Tailed Markov Decision Processes
86. ICML 2026Better, Faster: Harnessing Self-Improvement in Large Reasoning Models
87. ICML 2026Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization
88. ICML 2026Beyond Heuristics: Learnable Density Control for 3D Gaussian Splatting
89. ICML 2026Beyond Majority Voting: Self-Reflective Test-Time Reinforcement Learning for LLM Reasoning
90. ICML 2026Beyond Mode Collapse: Distribution Matching for Diverse Reasoning
91. ICML 2026Beyond Normalization: Rethinking the Partition Function as a Difficulty Scheduler for RLVR
92. ICML 2026Beyond Policy Training: Recursive Solution Search from Unannotated Videos
93. ICML 2026Beyond Rewards in RL for Cyber Defence
94. ICML 2026Beyond Softmax: A Natural Parameterization for Categorical Random Variables
95. ICML 2026Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQL
96. ICML 2026Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning
97. ICML 2026Beyond the Bellman Recursion: A Pontryagin-Guided Framework for Non-Exponential Discounting
98. ICML 2026Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training
99. ICML 2026Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning
100. ICML 2026Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic 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。