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 84 篇，第 2 / 2 页

51. ICLR 2024Online GNN Evaluation Under Test-time Graph Distribution Shifts
52. ICLR 2024OpenTab: Advancing Large Language Models as Open-domain Table Reasoners
53. ICLR 2024OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text
54. ICLR 2024Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
55. ICLR 2024PROGRAM: PROtotype GRAph Model based Pseudo-Label Learning for Test-Time Adaptation
56. ICLR 2024Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
57. ICLR 2024REFACTOR: Learning to Extract Theorems from Proofs
58. ICLR 2024Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models
59. ICLR 2024SaNN: Simple Yet Powerful Simplicial-aware Neural Networks
60. ICLR 2024SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos
61. ICLR 2024Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation
62. ICLR 2024SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning
63. ICLR 2024Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
64. ICLR 2024Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM
65. ICLR 2024Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models
66. ICLR 2024Teaching Arithmetic to Small Transformers
67. ICLR 2024Test-time Adaptation against Multi-modal Reliability Bias
68. ICLR 2024Test-Time Training on Nearest Neighbors for Large Language Models
69. ICLR 2024TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series
70. ICLR 2024The Expressive Power of Transformers with Chain of Thought
71. ICLR 2024The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction
72. ICLR 2024Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
73. ICLR 2024THOUGHT PROPAGATION: AN ANALOGICAL APPROACH TO COMPLEX REASONING WITH LARGE LANGUAGE MODELS
74. ICLR 2024TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning
75. ICLR 2024ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
76. ICLR 2024Towards Foundation Models for Knowledge Graph Reasoning
77. ICLR 2024Towards Generative Abstract Reasoning: Completing Raven’s Progressive Matrix via Rule Abstraction and Selection
78. ICLR 2024Towards Robust Multi-Modal Reasoning via Model Selection
79. ICLR 2024Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlation
80. ICLR 2024Understanding Expressivity of GNN in Rule Learning
81. ICLR 2024ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation
82. ICLR 2024Video Decomposition Prior: Editing Videos Layer by Layer
83. ICLR 2024What Algorithms can Transformers Learn? A Study in Length Generalization
84. ICLR 2024When can transformers reason with abstract symbols?

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。