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 21 / 26 页

  1. NeurIPS 2023Autonomous Capability Assessment of Sequential Decision-Making Systems in Stochastic Settings
  2. NeurIPS 2023Benchmarking Large Language Models on CMExam - A comprehensive Chinese Medical Exam Dataset
  3. NeurIPS 2023Beyond Invariance: Test-Time Label-Shift Adaptation for Addressing "Spurious" Correlations
  4. NeurIPS 2023BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information
  5. NeurIPS 2023Boosting Adversarial Transferability by Achieving Flat Local Maxima
  6. NeurIPS 2023Budgeting Counterfactual for Offline RL
  7. NeurIPS 2023Building the Bridge of Schrödinger: A Continuous Entropic Optimal Transport Benchmark
  8. NeurIPS 2023BuildingsBench: A Large-Scale Dataset of 900K Buildings and Benchmark for Short-Term Load Forecasting
  9. NeurIPS 2023Can Language Models Solve Graph Problems in Natural Language?
  10. NeurIPS 2023Can Language Models Teach? Teacher Explanations Improve Student Performance via Personalization
  11. NeurIPS 2023Causal Interpretation of Self-Attention in Pre-Trained Transformers
  12. NeurIPS 2023Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback
  13. NeurIPS 2023Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models
  14. NeurIPS 2023Change point detection and inference in multivariate non-parametric models under mixing conditions
  15. NeurIPS 2023Characterizing the Optimal $0-1$ Loss for Multi-class Classification with a Test-time Attacker
  16. NeurIPS 2023Circuit as Set of Points
  17. NeurIPS 2023CLadder: Assessing Causal Reasoning in Language Models
  18. NeurIPS 2023Classification of Heavy-tailed Features in High Dimensions: a Superstatistical Approach
  19. NeurIPS 2023CLeAR: Continual Learning on Algorithmic Reasoning for Human-like Intelligence
  20. NeurIPS 2023Collaborative Alignment of NLP Models
  21. NeurIPS 2023Computing a human-like reaction time metric from stable recurrent vision models
  22. NeurIPS 2023Concentration analysis of multivariate elliptic diffusions
  23. NeurIPS 2023Conditional independence testing under misspecified inductive biases
  24. NeurIPS 2023Coneheads: Hierarchy Aware Attention
  25. NeurIPS 2023Continuous-Time Functional Diffusion Processes
  26. NeurIPS 2023Contrastive Sampling Chains in Diffusion Models
  27. NeurIPS 2023Convergence analysis of ODE models for accelerated first-order methods via positive semidefinite kernels
  28. NeurIPS 2023Convergence of mean-field Langevin dynamics: time-space discretization, stochastic gradient, and variance reduction
  29. NeurIPS 2023Counterfactual Memorization in Neural Language Models
  30. NeurIPS 2023DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models
  31. NeurIPS 2023Decoding the Enigma: Benchmarking Humans and AIs on the Many Facets of Working Memory
  32. NeurIPS 2023Deductive Verification of Chain-of-Thought Reasoning
  33. NeurIPS 2023DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection
  34. NeurIPS 2023Demo2Code: From Summarizing Demonstrations to Synthesizing Code via Extended Chain-of-Thought
  35. NeurIPS 2023Differentiable Neuro-Symbolic Reasoning on Large-Scale Knowledge Graphs
  36. NeurIPS 2023Differentiable Sampling of Categorical Distributions Using the CatLog-Derivative Trick
  37. NeurIPS 2023Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence
  38. NeurIPS 2023Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback
  39. NeurIPS 2023DIFUSCO: Graph-based Diffusion Solvers for Combinatorial Optimization
  40. NeurIPS 2023Diplomat: A Dialogue Dataset for Situated PragMATic Reasoning
  41. NeurIPS 2023Dis-inhibitory neuronal circuits can control the sign of synaptic plasticity
  42. NeurIPS 2023Discriminative Calibration: Check Bayesian Computation from Simulations and Flexible Classifier
  43. NeurIPS 2023DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models
  44. NeurIPS 2023Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning
  45. NeurIPS 2023Dissecting Chain-of-Thought: Compositionality through In-Context Filtering and Learning
  46. NeurIPS 2023Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation
  47. NeurIPS 2023Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration
  48. NeurIPS 2023Does Visual Pretraining Help End-to-End Reasoning?
  49. NeurIPS 2023Effective Robustness against Natural Distribution Shifts for Models with Different Training Data
  50. NeurIPS 2023Egocentric Planning for Scalable Embodied Task Achievement

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