推理模型论文趋势 2023–2026

主要结论

• 推理模型论文从 2023 年的 470 篇增长到 2026 年的 1,799 篇，三年间扩大到约 3.8 倍。
• NeurIPS 是发推理模型论文最多的会议，2023–2026 年共 1,253 篇，占四个会议总量的 36%。
• 交叉方向里涨得最快的是强化学习：同时属于两个主题的论文从 2023 年的 9 篇增至 2026 年的 437 篇。
• 在「前沿系统」的 4 个主题里，它的 2026 年论文数排第 3；同组增长最快的AI 智能体是 12 倍，推理模型是 3.8 倍。

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 2026A Mechanistic Analysis of Looped Reasoning Language Models
• ICML 2026A Formal Comparison Between Chain of Thought and Latent Thought
• ICLR 2026A Simple "Motivation" Can Enhance Reinforcement Finetuning of Large Reasoning Models
• CVPR 2026Asking like Socrates Socrates helps VLMs understand remote sensing images
• NeurIPS 2025A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1
• ICML 2025A Reasoning-Based Approach to Cryptic Crossword Clue Solving
• ICLR 2025A Formal Framework for Understanding Length Generalization in Transformers
• CVPR 2025Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought
• NeurIPS 2024Are Large Language Models Good Statisticians?
• ICML 2024Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
• ICLR 2024Amortizing intractable inference in large language models
• CVPR 2024Generate Subgoal Images before Act: Unlocking the Chain-of-Thought Reasoning in Diffusion Model for Robot Manipulation with Multimodal Prompts
• NeurIPS 2023A benchmark of categorical encoders for binary classification
• ICML 2023Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?
• ICLR 2023Automatic Chain of Thought Prompting in Large Language Models
• CVPR 2023ActMAD: Activation Matching To Align Distributions for Test-Time-Training
• NeurIPS 2026A Solvable Model of Chain-of-Thought in In-Context Learning
• ICML 2026A Narrowing Geometry in Contaminated Reasoning
• ICLR 2026A State-Transition Framework for Efficient LLM Reasoning
• CVPR 2026Beyond Weak Supervision MLLMs-Guided Graded Knowledge Distillation for Unsupervised Camouflaged

全部推理模型论文

共 204 篇，第 3 / 5 页

101. CVPR 2026LocateAnything3D Vision-Language 3D Detection with Chain-of-Sight
102. CVPR 2026LongVideo-R1 Smart Navigation for Low-cost Long Video Understanding
103. CVPR 2026LongVT Incentivizing Thinking with Long Videos via Native Tool Calling
104. CVPR 2026Masking Matters Unlocking the Spatial Reasoning Capabilities of LLMs for
105. CVPR 2026Meta-CoT Enhancing Granularity and Generalization in Image Editing
106. CVPR 2026Mimic Human Cognition Master Multi-Image Reasoning A Meta-Action Framework for
107. CVPR 2026MindDriver Introducing Progressive Multimodal Reasoning for Autonomous Driving
108. CVPR 2026Minerva-Ego Spatiotemporal Hints for Egocentric Video Understanding
109. CVPR 2026Mixture of Prototypes for Test-time Adaptive Segmentation
110. CVPR 2026MMSD3.0 A Multi-Image Benchmark for Real-World Multimodal Sarcasm Detection
111. CVPR 2026MMTIT-Bench A Multilingual and Multi-Scenario Benchmark with Cognition-Perception-Reasoning Guided Text-Image
112. CVPR 2026Multi-modal Test-time Adaptation via Adaptive Probabilistic Gaussian Calibration
113. CVPR 2026Nano-EmoX Unifying Multimodal Emotional Intelligence from Perception to Empathy
114. CVPR 2026NEAF Natural Image Editing with Attention Fusion for Generalizable Test-time
115. CVPR 2026Neural Collapse in Test-Time Adaptation
116. CVPR 2026OASIS On-Demand Hierarchical Event Memory for Streaming Video Reasoning
117. CVPR 2026Obstruction Reasoning for Robotic Grasping
118. CVPR 2026OctoMed Data Recipes for State-of-the-Art Multimodal Medical Reasoning
119. CVPR 2026OmniVTG A Large-Scale Dataset and Training Paradigm for Open-World Video
120. CVPR 2026OneThinker All-in-one Reasoning Model for Image and Video
121. CVPR 2026OralGPT-Omni A Versatile Dental Multimodal Large Language Model
122. CVPR 2026OVOD-Agent A Markov-Bandit Framework for Proactive Visual Reasoning and Self-Evolving
123. CVPR 2026Parse Search and Confirmation Training-Free Aerial Vision-and-Dialog Navigation with Chain-of-Thought
124. CVPR 2026Perceiving the Near Reasoning the Distant Coherent Long-Horizon Trajectory Prediction
125. CVPR 2026Perceptual Neural Video Compression with Color Separation and Rank Chain
126. CVPR 2026PGR-Net Prior-Guided ROI Reasoning Network for Brain Tumor MRI Segmentation
127. CVPR 2026PixDLM A Dual-Path Multimodal Language Model for UAV Reasoning Segmentation
128. CVPR 2026POINTS-Long Adaptive Dual-Mode Visual Reasoning in MLLMs
129. CVPR 2026PointThinker Point-Incentivized Parallel Thinking for Multimodal Large Language Model
130. CVPR 2026PoseGAM Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning
131. CVPR 2026PRISM Prototype-based Reasoning with Inter-modal Semantic Mining for Interpretable Image
132. CVPR 2026Probabilistic Concept Graph Reasoning for Multimodal Misinformation Detection
133. CVPR 2026Probing and Bridging Geometry-Interaction Cues for Affordance Reasoning in Vision
134. CVPR 2026Progress by Pieces Test-Time Scaling for Autoregressive Image Generation
135. CVPR 2026PromptEnhancer Taming Your Rewriter for Text-to-Image Generation via Fine-Grained Reward
136. CVPR 2026Proof-of-Perception Certified Tool-Using Multimodal Reasoning with Compositional Conformal Guarantees
137. CVPR 2026R-4B Incentivizing General-Purpose Auto-Thinking in MLLMs via Bi-Mode Annealing and
138. CVPR 2026R2-Seg Training-Free OOD Medical Tumor Segmentation via Anatomical Reasoning and
139. CVPR 2026Rationale-Enhanced Decoding for Multi-modal Chain-of-Thought
140. CVPR 2026Re-Align Structured Reasoning-guided Alignment for In-Context Image Generation and Editing
141. CVPR 2026ReaGEN Adaptive Generation of Structured Chains-of-Thought for Efficient Multimodal Reasoning
142. CVPR 2026ReAlign Generalizable Image Forgery Detection via Reasoning-Aligned Representation
143. CVPR 2026Reallocating Attention Across Layers to Reduce Multimodal Hallucination
144. CVPR 2026ReasonEdit Towards Reasoning-Enhanced Image Editing Models
145. CVPR 2026Reasoning Diffusion for Unpaired Test Time Out-of-distribution Text-Image to Video
146. CVPR 2026ReasonMap Towards Fine-Grained Visual Reasoning from Transit Maps
147. CVPR 2026Reinforcing Structured Chain-of-Thought for Video Understanding
148. CVPR 2026Reinforcing Video Object Segmentation to Think before it Segments
149. CVPR 2026ReLaX Reasoning with Latent Exploration for Large Reasoning Models
150. CVPR 2026Revisiting the Necessity of Lengthy Chain-of-Thought in Vision-centric Reasoning Generalization

常见问题

2023–2026 年四大会议一共有多少篇推理模型论文？

共 3,512 篇，按年份分别是 2023 年 470 篇、2024 年 311 篇、2025 年 932 篇、2026 年 1,799 篇。

NeurIPS 2026 有多少篇推理模型论文？

NeurIPS 2026 有 361 篇推理模型论文，上一届是 500 篇。

ICLR 2026 有多少篇推理模型论文？

ICLR 2026 有 652 篇推理模型论文，上一届是 203 篇。

ICML 2026 有多少篇推理模型论文？

ICML 2026 有 582 篇推理模型论文，上一届是 159 篇。

CVPR 2026 有多少篇推理模型论文？

CVPR 2026 有 204 篇推理模型论文，上一届是 70 篇。

哪个会议的推理模型论文最多？

NeurIPS，2023–2026 年共 1,253 篇。