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 311 篇，第 2 / 7 页

51. ICLR 2024Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs
52. ICLR 2024Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World
53. ICLR 2024Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models
54. ICLR 2024Can Large Language Models Infer Causation from Correlation?
55. ICLR 2024Causal Modelling Agents: Causal Graph Discovery through Synergising Metadata- and Data-driven Reasoning
56. ICLR 2024Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources
57. ICLR 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding
58. ICLR 2024CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules
59. ICLR 2024COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits
60. ICLR 2024CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models
61. ICLR 2024Continual Momentum Filtering on Parameter Space for Online Test-time Adaptation
62. ICLR 2024CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets
63. ICLR 2024Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
64. ICLR 2024DQ-LoRe: Dual Queries with Low Rank Approximation Re-ranking for In-Context Learning
65. ICLR 2024DSPy: Compiling Declarative Language Model Calls into State-of-the-Art Pipelines
66. ICLR 2024DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks
67. ICLR 2024Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors
68. ICLR 2024Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
69. ICLR 2024GENOME: Generative Neuro-Symbolic Visual Reasoning by Growing and Reusing Modules
70. ICLR 2024Hypothesis Search: Inductive Reasoning with Language Models
71. ICLR 2024I-PHYRE: Interactive Physical Reasoning
72. ICLR 2024LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving
73. ICLR 2024Large Language Model Cascades with Mixture of Thought Representations for Cost-Efficient Reasoning
74. ICLR 2024Large Language Models as Analogical Reasoners
75. ICLR 2024Large Language Models Cannot Self-Correct Reasoning Yet
76. ICLR 2024Learning Performance-Improving Code Edits
77. ICLR 2024Lemur: Harmonizing Natural Language and Code for Language Agents
78. ICLR 2024Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs
79. ICLR 2024Let's Verify Step by Step
80. ICLR 2024LLCP: Learning Latent Causal Processes for Reasoning-based Video Question Answer
81. ICLR 2024Llemma: An Open Language Model for Mathematics
82. ICLR 2024Look, Remember and Reason: Grounded Reasoning in Videos with Language Models
83. ICLR 2024Magnushammer: A Transformer-Based Approach to Premise Selection
84. ICLR 2024MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning
85. ICLR 2024MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
86. ICLR 2024MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
87. ICLR 2024MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning
88. ICLR 2024MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data
89. ICLR 2024Neural Language of Thought Models
90. ICLR 2024On the generalization capacity of neural networks during generic multimodal reasoning
91. ICLR 2024On the Markov Property of Neural Algorithmic Reasoning: Analyses and Methods
92. ICLR 2024On the Power of the Weisfeiler-Leman Test for Graph Motif Parameters
93. ICLR 2024On the Variance of Neural Network Training with respect to Test Sets and Distributions
94. ICLR 2024Online GNN Evaluation Under Test-time Graph Distribution Shifts
95. ICLR 2024OpenTab: Advancing Large Language Models as Open-domain Table Reasoners
96. ICLR 2024OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text
97. ICLR 2024Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
98. ICLR 2024PROGRAM: PROtotype GRAph Model based Pseudo-Label Learning for Test-Time Adaptation
99. ICLR 2024Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
100. ICLR 2024REFACTOR: Learning to Extract Theorems from Proofs

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。