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 913 篇，第 15 / 19 页

  1. ICML 2025SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior
  2. ICML 2025Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification
  3. ICML 2025Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search
  4. ICML 2025Scaling Test-Time Compute Without Verification or RL is Suboptimal
  5. ICML 2025Self-Consistency Preference Optimization
  6. ICML 2025ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
  7. ICML 2025Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration
  8. ICML 2025Spatial Reasoning with Denoising Models
  9. ICML 2025Stability and Generalization Capability of Subgraph Reasoning Models for Inductive Knowledge Graph Completion
  10. ICML 2025STAIR: Improving Safety Alignment with Introspective Reasoning
  11. ICML 2025STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving
  12. ICML 2025T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling
  13. ICML 2025Task Generalization with Autoregressive Compositional Structure: Can Learning from $D$ Tasks Generalize to $D^T$ Tasks?
  14. ICML 2025Teaching Transformers Causal Reasoning through Axiomatic Training
  15. ICML 2025Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized Prototypes
  16. ICML 2025Test-Time Canonicalization by Foundation Models for Robust Perception
  17. ICML 2025Test-time Correlation Alignment
  18. ICML 2025Test-Time Learning for Large Language Models
  19. ICML 2025Test-Time Selective Adaptation for Uni-Modal Distribution Shift in Multi-Modal Data
  20. ICML 2025Test-Time Training Provably Improves Transformers as In-context Learners
  21. ICML 2025The Surprising Effectiveness of Test-Time Training for Few-Shot Learning
  22. ICML 2025Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization
  23. ICML 2025Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
  24. ICML 2025Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models
  25. ICML 2025TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language Generation
  26. ICML 2025UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models
  27. ICML 2025Understanding Chain-of-Thought in LLMs through Information Theory
  28. ICML 2025Understanding the Logic of Direct Preference Alignment through Logic
  29. ICML 2025Universal Length Generalization with Turing Programs
  30. ICML 2025unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning
  31. ICML 2025Variational Counterfactual Intervention Planning to Achieve Target Outcomes
  32. ICML 2025VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data
  33. ICML 2025video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model
  34. ICML 2025Visual and Domain Knowledge for Professional-level Graph-of-Thought Medical Reasoning
  35. ICML 2025Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models
  36. ICML 2025What Do Learning Dynamics Reveal About Generalization in LLM Mathematical Reasoning?
  37. ICML 2025Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
  38. ICML 2025Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas
  39. ICML 2025WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving
  40. ICML 2025World Model Implanting for Test-time Adaptation of Embodied Agents
  41. ICML 2025ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning
  42. ICML 2024Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
  43. ICML 2024Analysis for Abductive Learning and Neural-Symbolic Reasoning Shortcuts
  44. ICML 2024Auto-Regressive Next-Token Predictors are Universal Learners
  45. ICML 2024BAT: Learning to Reason about Spatial Sounds with Large Language Models
  46. ICML 2024Chain of Code: Reasoning with a Language Model-Augmented Code Emulator
  47. ICML 2024Chain-of-Thought Predictive Control
  48. ICML 2024CogBench: a large language model walks into a psychology lab
  49. ICML 2024Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks
  50. ICML 2024Compute Better Spent: Replacing Dense Layers with Structured Matrices

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