推理模型论文趋势 2023–2026
链式推理、测试时计算与显式推理能力
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 3,512 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 271 | 57 | 109 | 33 | 470 |
| 2024 | 121 | 84 | 63 | 43 | 311 |
| 2025 | 500 | 203 | 159 | 70 | 932 |
| 2026 | 361 | 652 | 582 | 204 | 1,799 |
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 203 篇，第 4 / 5 页
- ICLR 2025SegLLM: Multi-round Reasoning Segmentation with Large Language Models
- ICLR 2025Selective Label Enhancement Learning for Test-Time Adaptation
- ICLR 2025Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning
- ICLR 2025Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling
- ICLR 2025SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models
- ICLR 2025Stabilized Neural Prediction of Potential Outcomes in Continuous Time
- ICLR 2025Steering Large Language Models between Code Execution and Textual Reasoning
- ICLR 2025Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo
- ICLR 2025Storybooth: Training-Free Multi-Subject Consistency for Improved Visual Storytelling
- ICLR 2025SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction
- ICLR 2025SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement
- ICLR 2025Systematic Relational Reasoning With Epistemic Graph Neural Networks
- ICLR 2025Systems with Switching Causal Relations: A Meta-Causal Perspective
- ICLR 2025Tell me about yourself: LLMs are aware of their learned behaviors
- ICLR 2025Temporal Reasoning Transfer from Text to Video
- ICLR 2025Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning
- ICLR 2025Test-Time Adaptation for Combating Missing Modalities in Egocentric Videos
- ICLR 2025Test-time Adaptation for Cross-modal Retrieval with Query Shift
- ICLR 2025Test-time Adaptation for Image Compression with Distribution Regularization
- ICLR 2025Test-time Adaptation for Regression by Subspace Alignment
- ICLR 2025Test-Time Ensemble via Linear Mode Connectivity: A Path to Better Adaptation
- ICLR 2025The Belief State Transformer
- ICLR 2025The Labyrinth of Links: Navigating the Associative Maze of Multi-modal LLMs
- ICLR 2025Think Thrice Before You Act: Progressive Thought Refinement in Large Language Models
- ICLR 2025Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation
- ICLR 2025ThinkBot: Embodied Instruction Following with Thought Chain Reasoning
- ICLR 2025Time After Time: Deep-Q Effect Estimation for Interventions on When and What to do
- ICLR 2025To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
- ICLR 2025To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts
- ICLR 2025Token-Supervised Value Models for Enhancing Mathematical Problem-Solving Capabilities of Large Language Models
- ICLR 2025TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models
- ICLR 2025ToolGen: Unified Tool Retrieval and Calling via Generation
- ICLR 2025Training Language Models on Synthetic Edit Sequences Improves Code Synthesis
- ICLR 2025Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis
- ICLR 2025Training on the Test Task Confounds Evaluation and Emergence
- ICLR 2025Transformer Encoder Satisfiability: Complexity and Impact on Formal Reasoning
- ICLR 2025Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought
- ICLR 2025Transformers Provably Solve Parity Efficiently with Chain of Thought
- ICLR 2025Transformers Struggle to Learn to Search
- ICLR 2025TTVD: Towards a Geometric Framework for Test-Time Adaptation Based on Voronoi Diagram
- ICLR 2025TypedThinker: Diversify Large Language Model Reasoning with Typed Thinking
- ICLR 2025UGMathBench: A Diverse and Dynamic Benchmark for Undergraduate-Level Mathematical Reasoning with Large Language Models
- ICLR 2025UniCoTT: A Unified Framework for Structural Chain-of-Thought Distillation
- ICLR 2025Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and Amendment
- ICLR 2025Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only
- ICLR 2025Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision
- ICLR 2025Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs
- ICLR 2025Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts Reasoning
- ICLR 2025VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning
- ICLR 2025Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查推理模型在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "reasoning-models"}
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。