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 996 篇，第 19 / 20 页

  1. ICLR 2024Neural Language of Thought Models
  2. ICLR 2024On the generalization capacity of neural networks during generic multimodal reasoning
  3. ICLR 2024On the Markov Property of Neural Algorithmic Reasoning: Analyses and Methods
  4. ICLR 2024On the Power of the Weisfeiler-Leman Test for Graph Motif Parameters
  5. ICLR 2024On the Variance of Neural Network Training with respect to Test Sets and Distributions
  6. ICLR 2024Online GNN Evaluation Under Test-time Graph Distribution Shifts
  7. ICLR 2024OpenTab: Advancing Large Language Models as Open-domain Table Reasoners
  8. ICLR 2024OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text
  9. ICLR 2024Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
  10. ICLR 2024PROGRAM: PROtotype GRAph Model based Pseudo-Label Learning for Test-Time Adaptation
  11. ICLR 2024Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
  12. ICLR 2024REFACTOR: Learning to Extract Theorems from Proofs
  13. ICLR 2024Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models
  14. ICLR 2024SaNN: Simple Yet Powerful Simplicial-aware Neural Networks
  15. ICLR 2024SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos
  16. ICLR 2024Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation
  17. ICLR 2024SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning
  18. ICLR 2024Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
  19. ICLR 2024Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM
  20. ICLR 2024Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models
  21. ICLR 2024Teaching Arithmetic to Small Transformers
  22. ICLR 2024Test-time Adaptation against Multi-modal Reliability Bias
  23. ICLR 2024Test-Time Training on Nearest Neighbors for Large Language Models
  24. ICLR 2024TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series
  25. ICLR 2024The Expressive Power of Transformers with Chain of Thought
  26. ICLR 2024The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction
  27. ICLR 2024Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
  28. ICLR 2024THOUGHT PROPAGATION: AN ANALOGICAL APPROACH TO COMPLEX REASONING WITH LARGE LANGUAGE MODELS
  29. ICLR 2024TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning
  30. ICLR 2024ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
  31. ICLR 2024Towards Foundation Models for Knowledge Graph Reasoning
  32. ICLR 2024Towards Generative Abstract Reasoning: Completing Raven’s Progressive Matrix via Rule Abstraction and Selection
  33. ICLR 2024Towards Robust Multi-Modal Reasoning via Model Selection
  34. ICLR 2024Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlation
  35. ICLR 2024Understanding Expressivity of GNN in Rule Learning
  36. ICLR 2024ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation
  37. ICLR 2024Video Decomposition Prior: Editing Videos Layer by Layer
  38. ICLR 2024What Algorithms can Transformers Learn? A Study in Length Generalization
  39. ICLR 2024When can transformers reason with abstract symbols?
  40. ICLR 2023A Learning Based Hypothesis Test for Harmful Covariate Shift
  41. ICLR 2023A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics
  42. ICLR 2023Automatic Chain of Thought Prompting in Large Language Models
  43. ICLR 2023Can Neural Networks Learn Implicit Logic from Physical Reasoning?
  44. ICLR 2023Can We Faithfully Represent Absence States to Compute Shapley Values on a DNN?
  45. ICLR 2023Causal Reasoning in the Presence of Latent Confounders via Neural ADMG Learning
  46. ICLR 2023Combinatorial-Probabilistic Trade-Off: P-Values of Community Properties Test in the Stochastic Block Models
  47. ICLR 2023Complexity-Based Prompting for Multi-step Reasoning
  48. ICLR 2023Decomposed Prompting: A Modular Approach for Solving Complex Tasks
  49. ICLR 2023DELTA: DEGRADATION-FREE FULLY TEST-TIME ADAPTATION
  50. ICLR 2023Dual Algorithmic Reasoning

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