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 3,512 篇，第 1 / 71 页

1. CVPR 20263D Space as a Scratchpad for Editable Text-to-Image Generation
2. CVPR 2026A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large
3. CVPR 2026A3 Towards Advertising Aesthetic Assessment
4. CVPR 2026ACoT-VLA Action Chain-of-Thought for Vision-Language-Action Models
5. CVPR 2026Act2See Emergent Active Visual Perception for Video Reasoning
6. CVPR 2026Activation Matters Test-time Activated Negative Labels for OOD Detection with
7. CVPR 2026AcTTA Rethinking Test-Time Adaptation via Dynamic Activation
8. CVPR 2026Anchoring the Mind of Multimodal Reasoners Cognitive Bias as a
9. CVPR 2026APPO Attention-guided Perception Policy Optimization for Video Reasoning
10. CVPR 2026ARC Is a Vision Problem
11. CVPR 2026Are Image-to-Video Models Good Zero-Shot Image Editors
12. CVPR 2026Asking like Socrates Socrates helps VLMs understand remote sensing images
13. CVPR 2026AutoTraces Autoregressive Trajectory Forecasting via Multimodal Large Language Models
14. CVPR 2026Beyond Weak Supervision MLLMs-Guided Graded Knowledge Distillation for Unsupervised Camouflaged
15. CVPR 2026Bootstrapping Multi-view Learning for Test-time Noisy Correspondence
16. CVPR 2026Can a Second-View Image Be a Language Geometric and Semantic
17. CVPR 2026Chain of Event-Centric Causal Thought for Physically Plausible Video Generation
18. CVPR 2026Chain-of-Frames Advancing Video Understanding in Multimodal LLMs via Frame-Aware Reasoning
19. CVPR 2026Chain-of-Thought Guided Multi-Modal Object Re-Identification
20. CVPR 2026Chart-FR1 Visual Focus-Driven Fine-Grained Reasoning on Dense Charts
21. CVPR 2026ChartR Evaluating Reasoning Accuracy and Robustness in Chart Question Answering
22. CVPR 2026Clinically-Grounded Counterfactual Reasoning for Medical Video Diagnosis
23. CVPR 2026CME-CAD Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generation
24. CVPR 2026CodeDance A Dynamic Tool-integrated MLLM for Executable Visual Reasoning
25. CVPR 2026CodeV Code with Images for Faithful Visual Reasoning via Tool-Aware
26. CVPR 2026ColaVLA Leveraging Cognitive Latent Reasoning for Hierarchical Parallel Trajectory Planning
27. CVPR 2026Compositional Transformation Reasoning for Composed Video Retrieval
28. CVPR 2026Context-Nav Context-Driven Exploration and Viewpoint-Aware 3D Spatial Reasoning for Instance
29. CVPR 2026CoT-Edit Let CoT Guide Instruction Video Editing
30. CVPR 2026Cross-Architecture Adaptation Cloud-Edge Continual Test-Time Adaptation with Dynamic Sampling and
31. CVPR 2026Cross-modal Fuzzy Alignment Network for Text-Aerial Person Retrieval and A
32. CVPR 2026Cut to the Chase Training-free Multimodal Summarization via Chain-of-Events
33. CVPR 2026D3D-VLP Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation
34. CVPR 2026Dance Across Shifts Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style
35. CVPR 2026DARC Dual Adjustment Reasoning with Counterfactuals for Trustworthy Chest X-ray
36. CVPR 2026Decompose and Transfer CoT-Prompting Enhanced Alignment for Open-Vocabulary Temporal Action
37. CVPR 2026Deconstructing the Failure of Ideal Noise Correction A Three-Pillar Diagnosis
38. CVPR 2026Decoupling Stability and Plasticity for Multi-Modal Test-Time Adaptation
39. CVPR 2026Deeper Thought Weaker Aim Understanding and Mitigating Perceptual Impairment during
40. CVPR 2026DENALI A Dataset Enabling Non-Line-of-Sight Spatial Reasoning with Low-Cost LiDARs
41. CVPR 2026Describe Anything Anywhere At Any Moment
42. CVPR 2026Diffusion Guided Chain-of-Vision for Large Autoregressive Vision Models
43. CVPR 2026dMLLM-TTS Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large
44. CVPR 2026Downscaling Intelligence Exploring Perception and Reasoning Bottlenecks in Small Multimodal
45. CVPR 2026DriveCombo Benchmarking Compositional Traffic Rule Reasoning in Autonomous Driving
46. CVPR 2026Dual Band Thermal Videography Separating Time-Varying Reflection and Emission Near
47. CVPR 2026Dual-level Adaptation for Multi-Object Tracking Building Test-Time Calibration from Experience
48. CVPR 2026EagleVision A Dual-Stage Framework with BEV-grounding-based Chain-of-Thought for Spatial Intelligence
49. CVPR 2026EduDiag A Benchmark for Educational Diagnostic Reasoning with Error Tracing
50. CVPR 2026Efficiency Follows Global-Local Decoupling

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。