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 1,253 篇，第 11 / 26 页

  1. NeurIPS 2025Enhancing Temporal Understanding in Video-LLMs through Stacked Temporal Attention in Vision Encoders
  2. NeurIPS 2025Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles
  3. NeurIPS 2025Evaluating Program Semantics Reasoning with Type Inference in System $F$
  4. NeurIPS 2025Evaluating the Inductive Abilities of Large Language Models: Why Chain-of-Thought Reasoning Sometimes Hurts More Than Helps
  5. NeurIPS 2025Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling
  6. NeurIPS 2025Evolutionary Reasoning Does Not Arise in Standard Usage of Protein Language Models
  7. NeurIPS 2025EvolvedGRPO: Unlocking Reasoning in LVLMs via Progressive Instruction Evolution
  8. NeurIPS 2025Exact Expressive Power of Transformers with Padding
  9. NeurIPS 2025Execution Guided Line-by-Line Code Generation
  10. NeurIPS 2025ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning
  11. NeurIPS 2025Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning
  12. NeurIPS 2025FALCON: An ML Framework for Fully Automated Layout-Constrained Analog Circuit Design
  13. NeurIPS 2025Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoning
  14. NeurIPS 2025Feature-Based Instance Neighbor Discovery: Advanced Stable Test-Time Adaptation in Dynamic World
  15. NeurIPS 2025FGBench: A Dataset and Benchmark for Molecular Property Reasoning at Functional Group-Level in Large Language Models
  16. NeurIPS 2025Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms
  17. NeurIPS 2025Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs
  18. NeurIPS 2025First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training
  19. NeurIPS 2025Fixed-Point RNNs: Interpolating from Diagonal to Dense
  20. NeurIPS 2025FlexAC: Towards Flexible Control of Associative Reasoning in Multimodal Large Language Models
  21. NeurIPS 2025Flexible Realignment of Language Models
  22. NeurIPS 2025FlySearch: Exploring how vision-language models explore
  23. NeurIPS 2025From Kolmogorov to Cauchy: Shallow XNet Surpasses KANs
  24. NeurIPS 2025From Sequence to Structure: Uncovering Substructure Reasoning in Transformers
  25. NeurIPS 2025FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving
  26. NeurIPS 2025General-Reasoner: Advancing LLM Reasoning Across All Domains
  27. NeurIPS 2025Generalizable Reasoning through Compositional Energy Minimization
  28. NeurIPS 2025Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers
  29. NeurIPS 2025Geometric Algorithms for Neural Combinatorial Optimization with Constraints
  30. NeurIPS 2025Geometry of Decision Making in Language Models
  31. NeurIPS 2025GoT: Unleashing Reasoning Capability of MLLM for Visual Generation and Editing
  32. NeurIPS 2025GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains
  33. NeurIPS 2025GRIP: A Graph-Based Reasoning Instruction Producer
  34. NeurIPS 2025GRIT: Teaching MLLMs to Think with Images
  35. NeurIPS 2025Grounded Reinforcement Learning for Visual Reasoning
  36. NeurIPS 2025GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
  37. NeurIPS 2025GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents
  38. NeurIPS 2025GUI-Rise: Structured Reasoning and History Summarization for GUI Navigation
  39. NeurIPS 2025Guiding LLM Decision-Making with Fairness Reward Models
  40. NeurIPS 2025GVPO: Group Variance Policy Optimization for Large Language Model Post-Training
  41. NeurIPS 2025Heterogeneous Adversarial Play in Interactive Environments
  42. NeurIPS 2025Hogwild! Inference: Parallel LLM Generation via Concurrent Attention
  43. NeurIPS 2025HoloLLM: Multisensory Foundation Model for Language-Grounded Human Sensing and Reasoning
  44. NeurIPS 2025How do Transformers Learn Implicit Reasoning?
  45. NeurIPS 2025How Far Are We from Optimal Reasoning Efficiency?
  46. NeurIPS 2025Hybrid Latent Reasoning via Reinforcement Learning
  47. NeurIPS 2025HypoBootstrap: A Bootstrapping Framework for Inductive Reasoning
  48. NeurIPS 2025ICPC-Eval: Probing the Frontiers of LLM Reasoning with Competitive Programming Contests
  49. NeurIPS 2025Improving Formal Reasoning of Transformer with State Stack
  50. NeurIPS 2025Incentivizing Dual Process Thinking for Efficient Large Language Model 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