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 913 篇，第 6 / 19 页
- ICML 2026Large Language Models as Topological Thinkers: A Benchmark on Graph Persistent Homology
- ICML 2026Large Language Models Explore by Latent Distilling
- ICML 2026LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoning
- ICML 2026LaST$_{0}$: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action Model
- ICML 2026Latent Reasoning in TRMs is Secretly a Policy Improvement Operator
- ICML 2026Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models
- ICML 2026Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens
- ICML 2026LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning
- ICML 2026Learnability-Informed Fine-Tuning of Diffusion Language Models
- ICML 2026Learning Context-Conditioned Predicate Semantics via Prototype Feedback
- ICML 2026Learning Rewrite-Invariant Reasoning with Targeted Alternation Training
- ICML 2026Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs
- ICML 2026Learning Structured Reasoning via Tractable Trajectory Control
- ICML 2026Learning to Correct: Reinforcement Learning for Multi-Attempt Chain-of-Thought
- ICML 2026Learning to Execute Graph Algorithms Exactly with Graph Neural Networks
- ICML 2026Learning to Memorize with Attributive and Associative Memory for Online Test-Time Adaptation of Vision-Language Models
- ICML 2026Learning to Reason for Factuality
- ICML 2026Learning to Theorize the World from Observation
- ICML 2026Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use
- ICML 2026Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models
- ICML 2026Less Is More: Fast and Accurate Reasoning with Cross-Head Unified Sparse Attention
- ICML 2026Leveraging Evidence Priors for Robust Prompt Learning under Noisy Supervision in Vision-Language Models
- ICML 2026Linearizing Vision Transformer with Test-Time Training
- ICML 2026LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?
- ICML 2026LLMInertia: Adaptive Counter-Inertial Reasoning to Improve Evidence Faithfulness in Large Language Models
- ICML 2026LMM4-IC4K: A Large Multimodal Model Powered Integrated Circuit Footprint Geometry Understanding
- ICML 2026LogicSAGE: Neuro-Symbolic Reasoning with Socratic-Guided Enhancement
- ICML 2026Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale
- ICML 2026LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning
- ICML 2026Look on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal Reasoning
- ICML 2026Lost in Context: Adressing Context Anxiety in Large Language Models
- ICML 2026Making Expert Reasoning Learnable with Self-Distillation
- ICML 2026MALICE: Memory-aware Loop Invariants Generation on Symbolic Execution Traces
- ICML 2026Many-Shot CoT-ICL: Making In-Context Learning Truly Learn
- ICML 2026Marrying Generative Model of Healthcare Events with Digital Twin of Social Determinants of Health for Disease Reasoning
- ICML 2026MathlibLemma: Folklore Lemma Generation and Benchmark for Formal Mathematics
- ICML 2026Maximum Likelihood Reinforcement Learning
- ICML 2026Measuring and Mitigating Post-Hoc Rationalization in Reverse Chain-of-Thought Generation
- ICML 2026MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks
- ICML 2026MedMosaic: A Challenging Large Scale Benchmark of Diverse Medical Audio
- ICML 2026MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning
- ICML 2026MentisOculi: Revealing the Limits of Reasoning with Mental Imagery
- ICML 2026MET-Bench: Multimodal Entity Tracking for Evaluating the Limitations of Vision-Language and Reasoning Models
- ICML 2026Mind the Gap: Catching Hallucinations via Evidence Drop on the Reasoning Manifold
- ICML 2026MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large Models
- ICML 2026Mining Useful General Data for Low-Resource Domain Adaptation
- ICML 2026Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior Adjustment
- ICML 2026Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time Scaling
- ICML 2026Mitigating the Safety–Utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
- ICML 2026MixReasoning: Switching Modes to Think
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。