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 159 篇，第 1 / 4 页

1. ICML 2025A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment
2. ICML 2025A Reasoning-Based Approach to Cryptic Crossword Clue Solving
3. ICML 2025A Sample Efficient Conditional Independence Test in the Presence of Discretization
4. ICML 2025Accelerating Large Language Model Reasoning via Speculative Search
5. ICML 2025AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism
6. ICML 2025AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence
7. ICML 2025Adversarial Reasoning at Jailbreaking Time
8. ICML 2025An Analysis for Reasoning Bias of Language Models with Small Initialization
9. ICML 2025An Architecture Search Framework for Inference-Time Techniques
10. ICML 2025Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
11. ICML 2025Bayesian Weight Enhancement with Steady-State Adaptation for Test-time Adaptation in Dynamic Environments
12. ICML 2025Benchmarking Abstract and Reasoning Abilities Through A Theoretical Perspective
13. ICML 2025BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute
14. ICML 2025Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning
15. ICML 2025Blink of an eye: a simple theory for feature localization in generative models
16. ICML 2025Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?
17. ICML 2025BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning
18. ICML 2025Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark
19. ICML 2025Can Transformers Reason Logically? A Study in SAT Solving
20. ICML 2025Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel
21. ICML 2025CodeIO: Condensing Reasoning Patterns via Code Input-Output Prediction
22. ICML 2025Compositional Causal Reasoning Evaluation in Language Models
23. ICML 2025Cost-efficient Collaboration between On-device and Cloud Language Models
24. ICML 2025CRANE: Reasoning with constrained LLM generation
25. ICML 2025Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM’s Reasoning Capability
26. ICML 2025Deliberation in Latent Space via Differentiable Cache Augmentation
27. ICML 2025Demonstration Selection for In-Context Learning via Reinforcement Learning
28. ICML 2025Demystifying Long Chain-of-Thought Reasoning
29. ICML 2025DiffusionVLA: Scaling Robot Foundation Models via Unified Diffusion and Autoregression
30. ICML 2025Discrete Neural Algorithmic Reasoning
31. ICML 2025Disentangling and Integrating Relational and Sensory Information in Transformer Architectures
32. ICML 2025Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning
33. ICML 2025Diving into Self-Evolving Training for Multimodal Reasoning
34. ICML 2025Do NOT Think That Much for 2+3=? On the Overthinking of Long Reasoning Models
35. ICML 2025DOLPHIN: A Programmable Framework for Scalable Neurosymbolic Learning
36. ICML 2025DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation
37. ICML 2025DyCodeEval: Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination
38. ICML 2025EditLord: Learning Code Transformation Rules for Code Editing
39. ICML 2025Efficiently Vectorized MCMC on Modern Accelerators
40. ICML 2025Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models
41. ICML 2025Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators
42. ICML 2025Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples
43. ICML 2025Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning
44. ICML 2025From Language Models over Tokens to Language Models over Characters
45. ICML 2025From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
46. ICML 2025Fully Dynamic Euclidean Bi-Chromatic Matching in Sublinear Update Time
47. ICML 2025Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
48. ICML 2025GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation
49. ICML 2025Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers
50. ICML 2025GSM-$\infty$: How Do your LLMs Behave over Infinitely Increasing Reasoning Complexity and Context Length?

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。