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 48 / 71 页

  1. NeurIPS 2025Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning
  2. NeurIPS 2025DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization
  3. NeurIPS 2025Distilling LLM Agent into Small Models with Retrieval and Code Tools
  4. NeurIPS 2025DLoFT: Gradient-Decoupled Fine-Tuning for Generalizable Long Chain-of-Thought Reasoning
  5. NeurIPS 2025DMWM: Dual-Mind World Model with Long-Term Imagination
  6. NeurIPS 2025Do LVLMs Truly Understand Video Anomalies? Revealing Hallucination via Co-Occurrence Patterns
  7. NeurIPS 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
  8. NeurIPS 2025Does Thinking More Always Help? Mirage of Test-Time Scaling in Reasoning Models
  9. NeurIPS 2025Don’t Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models
  10. NeurIPS 2025DreamPRM: Domain-reweighted Process Reward Model for Multimodal Reasoning
  11. NeurIPS 2025DrVD-Bench: Do Vision-Language Models Reason Like Human Doctors in Medical Image Diagnosis?
  12. NeurIPS 2025DSRF: A Dynamic and Scalable Reasoning Framework for Solving RPMs
  13. NeurIPS 2025DuetGraph: Coarse-to-Fine Knowledge Graph Reasoning with Dual-Pathway Global-Local Fusion
  14. NeurIPS 2025Dynamic Test-Time Compute Scaling in Control Policy: Difficulty-Aware Stochastic Interpolant Policy
  15. NeurIPS 2025EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test
  16. NeurIPS 2025Efficiently Scaling LLM Reasoning Programs with Certaindex
  17. NeurIPS 2025EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT
  18. NeurIPS 2025Eliciting Reasoning in Language Models with Cognitive Tools
  19. NeurIPS 2025Emergent Risk Awareness in Rational Agents under Resource Constraints
  20. NeurIPS 2025Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions
  21. NeurIPS 2025Enhancing Temporal Understanding in Video-LLMs through Stacked Temporal Attention in Vision Encoders
  22. NeurIPS 2025Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles
  23. NeurIPS 2025Evaluating Program Semantics Reasoning with Type Inference in System $F$
  24. NeurIPS 2025Evaluating the Inductive Abilities of Large Language Models: Why Chain-of-Thought Reasoning Sometimes Hurts More Than Helps
  25. NeurIPS 2025Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling
  26. NeurIPS 2025Evolutionary Reasoning Does Not Arise in Standard Usage of Protein Language Models
  27. NeurIPS 2025EvolvedGRPO: Unlocking Reasoning in LVLMs via Progressive Instruction Evolution
  28. NeurIPS 2025Exact Expressive Power of Transformers with Padding
  29. NeurIPS 2025Execution Guided Line-by-Line Code Generation
  30. NeurIPS 2025ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning
  31. NeurIPS 2025Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning
  32. NeurIPS 2025FALCON: An ML Framework for Fully Automated Layout-Constrained Analog Circuit Design
  33. NeurIPS 2025Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoning
  34. NeurIPS 2025Feature-Based Instance Neighbor Discovery: Advanced Stable Test-Time Adaptation in Dynamic World
  35. NeurIPS 2025FGBench: A Dataset and Benchmark for Molecular Property Reasoning at Functional Group-Level in Large Language Models
  36. NeurIPS 2025Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms
  37. NeurIPS 2025Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs
  38. NeurIPS 2025First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training
  39. NeurIPS 2025Fixed-Point RNNs: Interpolating from Diagonal to Dense
  40. NeurIPS 2025FlexAC: Towards Flexible Control of Associative Reasoning in Multimodal Large Language Models
  41. NeurIPS 2025Flexible Realignment of Language Models
  42. NeurIPS 2025FlySearch: Exploring how vision-language models explore
  43. NeurIPS 2025From Kolmogorov to Cauchy: Shallow XNet Surpasses KANs
  44. NeurIPS 2025From Sequence to Structure: Uncovering Substructure Reasoning in Transformers
  45. NeurIPS 2025FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving
  46. NeurIPS 2025General-Reasoner: Advancing LLM Reasoning Across All Domains
  47. NeurIPS 2025Generalizable Reasoning through Compositional Energy Minimization
  48. NeurIPS 2025Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers
  49. NeurIPS 2025Geometric Algorithms for Neural Combinatorial Optimization with Constraints
  50. NeurIPS 2025Geometry of Decision Making in 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