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 582 篇，第 6 / 12 页

  1. ICML 2026Large Language Models as Topological Thinkers: A Benchmark on Graph Persistent Homology
  2. ICML 2026Large Language Models Explore by Latent Distilling
  3. ICML 2026LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoning
  4. ICML 2026LaST$_{0}$: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action Model
  5. ICML 2026Latent Reasoning in TRMs is Secretly a Policy Improvement Operator
  6. ICML 2026Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models
  7. ICML 2026Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens
  8. ICML 2026LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning
  9. ICML 2026Learnability-Informed Fine-Tuning of Diffusion Language Models
  10. ICML 2026Learning Context-Conditioned Predicate Semantics via Prototype Feedback
  11. ICML 2026Learning Rewrite-Invariant Reasoning with Targeted Alternation Training
  12. ICML 2026Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs
  13. ICML 2026Learning Structured Reasoning via Tractable Trajectory Control
  14. ICML 2026Learning to Correct: Reinforcement Learning for Multi-Attempt Chain-of-Thought
  15. ICML 2026Learning to Execute Graph Algorithms Exactly with Graph Neural Networks
  16. ICML 2026Learning to Memorize with Attributive and Associative Memory for Online Test-Time Adaptation of Vision-Language Models
  17. ICML 2026Learning to Reason for Factuality
  18. ICML 2026Learning to Theorize the World from Observation
  19. ICML 2026Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use
  20. ICML 2026Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models
  21. ICML 2026Less Is More: Fast and Accurate Reasoning with Cross-Head Unified Sparse Attention
  22. ICML 2026Leveraging Evidence Priors for Robust Prompt Learning under Noisy Supervision in Vision-Language Models
  23. ICML 2026Linearizing Vision Transformer with Test-Time Training
  24. ICML 2026LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?
  25. ICML 2026LLMInertia: Adaptive Counter-Inertial Reasoning to Improve Evidence Faithfulness in Large Language Models
  26. ICML 2026LMM4-IC4K: A Large Multimodal Model Powered Integrated Circuit Footprint Geometry Understanding
  27. ICML 2026LogicSAGE: Neuro-Symbolic Reasoning with Socratic-Guided Enhancement
  28. ICML 2026Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale
  29. ICML 2026LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning
  30. ICML 2026Look on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal Reasoning
  31. ICML 2026Lost in Context: Adressing Context Anxiety in Large Language Models
  32. ICML 2026Making Expert Reasoning Learnable with Self-Distillation
  33. ICML 2026MALICE: Memory-aware Loop Invariants Generation on Symbolic Execution Traces
  34. ICML 2026Many-Shot CoT-ICL: Making In-Context Learning Truly Learn
  35. ICML 2026Marrying Generative Model of Healthcare Events with Digital Twin of Social Determinants of Health for Disease Reasoning
  36. ICML 2026MathlibLemma: Folklore Lemma Generation and Benchmark for Formal Mathematics
  37. ICML 2026Maximum Likelihood Reinforcement Learning
  38. ICML 2026Measuring and Mitigating Post-Hoc Rationalization in Reverse Chain-of-Thought Generation
  39. ICML 2026MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks
  40. ICML 2026MedMosaic: A Challenging Large Scale Benchmark of Diverse Medical Audio
  41. ICML 2026MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning
  42. ICML 2026MentisOculi: Revealing the Limits of Reasoning with Mental Imagery
  43. ICML 2026MET-Bench: Multimodal Entity Tracking for Evaluating the Limitations of Vision-Language and Reasoning Models
  44. ICML 2026Mind the Gap: Catching Hallucinations via Evidence Drop on the Reasoning Manifold
  45. ICML 2026MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large Models
  46. ICML 2026Mining Useful General Data for Low-Resource Domain Adaptation
  47. ICML 2026Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior Adjustment
  48. ICML 2026Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time Scaling
  49. ICML 2026Mitigating the Safety–Utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
  50. ICML 2026MixReasoning: Switching Modes to Think

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