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

每年论文数

各会议论文数

按年份和会议统计

推理模型论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20232715710933470
2024121846343311
202550020315970932
20263616525822041,799

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

全部推理模型论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 1,253 篇，第 22 / 26 页

  1. NeurIPS 2023EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought
  2. NeurIPS 2023Embracing the chaos: analysis and diagnosis of numerical instability in variational flows
  3. NeurIPS 2023Energy Discrepancies: A Score-Independent Loss for Energy-Based Models
  4. NeurIPS 2023Energy-Based Models for Anomaly Detection: A Manifold Diffusion Recovery Approach
  5. NeurIPS 2023Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning
  6. NeurIPS 2023Evaluating Cognitive Maps and Planning in Large Language Models with CogEval
  7. NeurIPS 2023Event Stream GPT: A Data Pre-processing and Modeling Library for Generative, Pre-trained Transformers over Continuous-time Sequences of Complex Events
  8. NeurIPS 2023Exact Bayesian Inference on Discrete Models via Probability Generating Functions: A Probabilistic Programming Approach
  9. NeurIPS 2023Exact Generalization Guarantees for (Regularized) Wasserstein Distributionally Robust Models
  10. NeurIPS 2023Exact recovery and Bregman hard clustering of node-attributed Stochastic Block Model
  11. NeurIPS 2023Exact Representation of Sparse Networks with Symmetric Nonnegative Embeddings
  12. NeurIPS 2023Exploring and Interacting with the Set of Good Sparse Generalized Additive Models
  13. NeurIPS 2023Exposing Attention Glitches with Flip-Flop Language Modeling
  14. NeurIPS 2023Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
  15. NeurIPS 2023Extending the Design Space of Graph Neural Networks by Rethinking Folklore Weisfeiler-Lehman
  16. NeurIPS 2023Faith and Fate: Limits of Transformers on Compositionality
  17. NeurIPS 2023Fantastic Robustness Measures: The Secrets of Robust Generalization
  18. NeurIPS 2023Fast Approximation of Similarity Graphs with Kernel Density Estimation
  19. NeurIPS 2023Fast Attention Requires Bounded Entries
  20. NeurIPS 2023Fast Scalable and Accurate Discovery of DAGs Using the Best Order Score Search and Grow Shrink Trees
  21. NeurIPS 2023Fed-CO$_{2}$: Cooperation of Online and Offline Models for Severe Data Heterogeneity in Federated Learning
  22. NeurIPS 2023FELM: Benchmarking Factuality Evaluation of Large Language Models
  23. NeurIPS 2023Finding Counterfactually Optimal Action Sequences in Continuous State Spaces
  24. NeurIPS 2023Generalizing Nonlinear ICA Beyond Structural Sparsity
  25. NeurIPS 2023GeoPhy: Differentiable Phylogenetic Inference via Geometric Gradients of Tree Topologies
  26. NeurIPS 2023Glance and Focus: Memory Prompting for Multi-Event Video Question Answering
  27. NeurIPS 2023GloptiNets: Scalable Non-Convex Optimization with Certificates
  28. NeurIPS 2023Goal Driven Discovery of Distributional Differences via Language Descriptions
  29. NeurIPS 2023GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients
  30. NeurIPS 2023GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation
  31. NeurIPS 2023Hierarchical VAEs provide a normative account of motion processing in the primate brain
  32. NeurIPS 2023How to Turn Your Knowledge Graph Embeddings into Generative Models
  33. NeurIPS 2023Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language
  34. NeurIPS 2023ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification
  35. NeurIPS 2023Imbalanced Mixed Linear Regression
  36. NeurIPS 2023Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability
  37. NeurIPS 2023Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners
  38. NeurIPS 2023In-Context Impersonation Reveals Large Language Models' Strengths and Biases
  39. NeurIPS 2023Interactive Visual Reasoning under Uncertainty
  40. NeurIPS 2023Intervention Generalization: A View from Factor Graph Models
  41. NeurIPS 2023Intriguing Properties of Quantization at Scale
  42. NeurIPS 2023Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts
  43. NeurIPS 2023Is Heterogeneity Notorious? Taming Heterogeneity to Handle Test-Time Shift in Federated Learning
  44. NeurIPS 2023iSCAN: Identifying Causal Mechanism Shifts among Nonlinear Additive Noise Models
  45. NeurIPS 2023Joint processing of linguistic properties in brains and language models
  46. NeurIPS 2023Kernel Stein Discrepancy thinning: a theoretical perspective of pathologies and a practical fix with regularization
  47. NeurIPS 2023Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks
  48. NeurIPS 2023Knowledge-based in silico models and dataset for the comparative evaluation of mammography AI for a range of breast characteristics, lesion conspicuities and doses
  49. NeurIPS 2023LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections
  50. NeurIPS 2023Language Is Not All You Need: Aligning Perception with Language Models

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"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「前沿系统」下的其他主题