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 58 / 71 页

  1. ICLR 2024Towards Generative Abstract Reasoning: Completing Raven’s Progressive Matrix via Rule Abstraction and Selection
  2. ICLR 2024Towards Robust Multi-Modal Reasoning via Model Selection
  3. ICLR 2024Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlation
  4. ICLR 2024Understanding Expressivity of GNN in Rule Learning
  5. ICLR 2024ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation
  6. ICLR 2024Video Decomposition Prior: Editing Videos Layer by Layer
  7. ICLR 2024What Algorithms can Transformers Learn? A Study in Length Generalization
  8. ICLR 2024When can transformers reason with abstract symbols?
  9. ICML 2024Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
  10. ICML 2024Analysis for Abductive Learning and Neural-Symbolic Reasoning Shortcuts
  11. ICML 2024Auto-Regressive Next-Token Predictors are Universal Learners
  12. ICML 2024BAT: Learning to Reason about Spatial Sounds with Large Language Models
  13. ICML 2024Chain of Code: Reasoning with a Language Model-Augmented Code Emulator
  14. ICML 2024Chain-of-Thought Predictive Control
  15. ICML 2024CogBench: a large language model walks into a psychology lab
  16. ICML 2024Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks
  17. ICML 2024Compute Better Spent: Replacing Dense Layers with Structured Matrices
  18. ICML 2024Conformal Predictions under Markovian Data
  19. ICML 2024ContPhy: Continuum Physical Concept Learning and Reasoning from Videos
  20. ICML 2024Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time
  21. ICML 2024Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training
  22. ICML 2024CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution
  23. ICML 2024Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shifts
  24. ICML 2024Do Efficient Transformers Really Save Computation?
  25. ICML 2024Dynamic Correlation Clustering in Sublinear Update Time
  26. ICML 2024Evaluation of Test-Time Adaptation Under Computational Time Constraints
  27. ICML 2024Extending Test-Time Augmentation with Metamorphic Relations for Combinatorial Problems
  28. ICML 2024Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigation
  29. ICML 2024Fully-Dynamic Approximate Decision Trees With Worst-Case Update Time Guarantees
  30. ICML 2024Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought
  31. ICML 2024GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements
  32. ICML 2024Graph-enhanced Large Language Models in Asynchronous Plan Reasoning
  33. ICML 2024How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?
  34. ICML 2024How Language Model Hallucinations Can Snowball
  35. ICML 2024Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD
  36. ICML 2024Improving Factuality and Reasoning in Language Models through Multiagent Debate
  37. ICML 2024In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought
  38. ICML 2024InfoNet: Neural Estimation of Mutual Information without Test-Time Optimization
  39. ICML 2024InstructSpeech: Following Speech Editing Instructions via Large Language Models
  40. ICML 2024Keypoint-based Progressive Chain-of-Thought Distillation for LLMs
  41. ICML 2024KnowFormer: Revisiting Transformers for Knowledge Graph Reasoning
  42. ICML 2024Language Agent Tree Search Unifies Reasoning, Acting, and Planning in Language Models
  43. ICML 2024Language Models with Conformal Factuality Guarantees
  44. ICML 2024Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs
  45. ICML 2024MathScale: Scaling Instruction Tuning for Mathematical Reasoning
  46. ICML 2024Matroid Semi-Bandits in Sublinear Time
  47. ICML 2024NExT: Teaching Large Language Models to Reason about Code Execution
  48. ICML 2024On the Independence Assumption in Neurosymbolic Learning
  49. ICML 2024Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs
  50. ICML 2024Premise Order Matters in Reasoning with Large 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