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 311 篇，第 4 / 7 页

  1. ICML 2024Graph-enhanced Large Language Models in Asynchronous Plan Reasoning
  2. ICML 2024How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?
  3. ICML 2024How Language Model Hallucinations Can Snowball
  4. ICML 2024Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD
  5. ICML 2024Improving Factuality and Reasoning in Language Models through Multiagent Debate
  6. ICML 2024In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought
  7. ICML 2024InfoNet: Neural Estimation of Mutual Information without Test-Time Optimization
  8. ICML 2024InstructSpeech: Following Speech Editing Instructions via Large Language Models
  9. ICML 2024Keypoint-based Progressive Chain-of-Thought Distillation for LLMs
  10. ICML 2024KnowFormer: Revisiting Transformers for Knowledge Graph Reasoning
  11. ICML 2024Language Agent Tree Search Unifies Reasoning, Acting, and Planning in Language Models
  12. ICML 2024Language Models with Conformal Factuality Guarantees
  13. ICML 2024Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs
  14. ICML 2024MathScale: Scaling Instruction Tuning for Mathematical Reasoning
  15. ICML 2024Matroid Semi-Bandits in Sublinear Time
  16. ICML 2024NExT: Teaching Large Language Models to Reason about Code Execution
  17. ICML 2024On the Independence Assumption in Neurosymbolic Learning
  18. ICML 2024Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs
  19. ICML 2024Premise Order Matters in Reasoning with Large Language Models
  20. ICML 2024Profile Reconstruction from Private Sketches
  21. ICML 2024Prompt Sketching for Large Language Models
  22. ICML 2024Promptbreeder: Self-Referential Self-Improvement via Prompt Evolution
  23. ICML 2024Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling
  24. ICML 2024Slot Abstractors: Toward Scalable Abstract Visual Reasoning
  25. ICML 2024Sparsest Models Elude Pruning: An Exposé of Pruning’s Current Capabilities
  26. ICML 2024StackSight: Unveiling WebAssembly through Large Language Models and Neurosymbolic Chain-of-Thought Decompilation
  27. ICML 2024Stationary Latent Weight Inference for Unreliable Observations from Online Test-Time Adaptation
  28. ICML 2024Stay on Topic with Classifier-Free Guidance
  29. ICML 2024STEER: Assessing the Economic Rationality of Large Language Models
  30. ICML 2024Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features
  31. ICML 2024Structured Chemistry Reasoning with Large Language Models
  32. ICML 2024Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning
  33. ICML 2024Test-Time Model Adaptation with Only Forward Passes
  34. ICML 2024Toward Adaptive Reasoning in Large Language Models with Thought Rollback
  35. ICML 2024Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model
  36. ICML 2024Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot
  37. ICML 2024Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation
  38. ICML 2024Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers
  39. ICML 2024Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition
  40. ICML 2024What Can Transformer Learn with Varying Depth? Case Studies on Sequence Learning Tasks
  41. NeurIPS 2024A Benchmark Suite for Systematically Evaluating Reasoning Shortcuts
  42. NeurIPS 2024A Careful Examination of Large Language Model Performance on Grade School Arithmetic
  43. NeurIPS 2024A Hitchhiker's Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning
  44. NeurIPS 2024A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts
  45. NeurIPS 2024A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoning
  46. NeurIPS 2024Are Large Language Models Good Statisticians?
  47. NeurIPS 2024AutoPSV: Automated Process-Supervised Verifier
  48. NeurIPS 2024BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning
  49. NeurIPS 2024Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects
  50. NeurIPS 2024Buffer of Thoughts: Thought-Augmented 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