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 3,512 篇，第 68 / 71 页

  1. NeurIPS 2023Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts
  2. NeurIPS 2023Is Heterogeneity Notorious? Taming Heterogeneity to Handle Test-Time Shift in Federated Learning
  3. NeurIPS 2023iSCAN: Identifying Causal Mechanism Shifts among Nonlinear Additive Noise Models
  4. NeurIPS 2023Joint processing of linguistic properties in brains and language models
  5. NeurIPS 2023Kernel Stein Discrepancy thinning: a theoretical perspective of pathologies and a practical fix with regularization
  6. NeurIPS 2023Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks
  7. 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
  8. NeurIPS 2023LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections
  9. NeurIPS 2023Language Is Not All You Need: Aligning Perception with Language Models
  10. NeurIPS 2023Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning
  11. NeurIPS 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting
  12. NeurIPS 2023Large Language Models are Visual Reasoning Coordinators
  13. NeurIPS 2023Large language models implicitly learn to straighten neural sentence trajectories to construct a predictive representation of natural language.
  14. NeurIPS 2023Large Language Models of Code Fail at Completing Code with Potential Bugs
  15. NeurIPS 2023Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions
  16. NeurIPS 2023LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
  17. NeurIPS 2023Learning Reliable Logical Rules with SATNet
  18. NeurIPS 2023Learning Rule-Induced Subgraph Representations for Inductive Relation Prediction
  19. NeurIPS 2023Learning to Reason and Memorize with Self-Notes
  20. NeurIPS 2023LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models
  21. NeurIPS 2023LLM-Pruner: On the Structural Pruning of Large Language Models
  22. NeurIPS 2023Localized Symbolic Knowledge Distillation for Visual Commonsense Models
  23. NeurIPS 2023LoRA: A Logical Reasoning Augmented Dataset for Visual Question Answering
  24. NeurIPS 2023Markovian Sliced Wasserstein Distances: Beyond Independent Projections
  25. NeurIPS 2023Massively Multilingual Corpus of Sentiment Datasets and Multi-faceted Sentiment Classification Benchmark
  26. NeurIPS 2023Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization
  27. NeurIPS 2023Minimum norm interpolation by perceptra: Explicit regularization and implicit bias
  28. NeurIPS 2023Mitigating the Popularity Bias of Graph Collaborative Filtering: A Dimensional Collapse Perspective
  29. NeurIPS 2023MMD Aggregated Two-Sample Test
  30. NeurIPS 2023MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks
  31. NeurIPS 2023Most Neural Networks Are Almost Learnable
  32. NeurIPS 2023Multi Time Scale World Models
  33. NeurIPS 2023MVDoppler: Unleashing the Power of Multi-View Doppler for MicroMotion-based Gait Classification
  34. NeurIPS 2023Near Optimal Reconstruction of Spherical Harmonic Expansions
  35. NeurIPS 2023Neural Algorithmic Reasoning Without Intermediate Supervision
  36. NeurIPS 2023Neural Foundations of Mental Simulation: Future Prediction of Latent Representations on Dynamic Scenes
  37. NeurIPS 2023Newton–Cotes Graph Neural Networks: On the Time Evolution of Dynamic Systems
  38. NeurIPS 2023Non-Asymptotic Analysis of a UCB-based Top Two Algorithm
  39. NeurIPS 2023Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts
  40. NeurIPS 2023Offline Imitation Learning with Variational Counterfactual Reasoning
  41. NeurIPS 2023On Calibrating Diffusion Probabilistic Models
  42. NeurIPS 2023On Sparse Modern Hopfield Model
  43. NeurIPS 2023On the Adversarial Robustness of Out-of-distribution Generalization Models
  44. NeurIPS 2023On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence
  45. NeurIPS 2023On the Convergence of CART under Sufficient Impurity Decrease Condition
  46. NeurIPS 2023On the Exploration of Local Significant Differences For Two-Sample Test
  47. NeurIPS 2023On the Generalization Error of Stochastic Mirror Descent for Quadratically-Bounded Losses: an Improved Analysis
  48. NeurIPS 2023On the Generalization Properties of Diffusion Models
  49. NeurIPS 2023On the Identifiability and Interpretability of Gaussian Process Models
  50. NeurIPS 2023On the Last-iterate Convergence in Time-varying Zero-sum Games: Extra Gradient Succeeds where Optimism Fails

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