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 43 / 71 页

  1. ICML 2025DiffusionVLA: Scaling Robot Foundation Models via Unified Diffusion and Autoregression
  2. ICML 2025Discrete Neural Algorithmic Reasoning
  3. ICML 2025Disentangling and Integrating Relational and Sensory Information in Transformer Architectures
  4. ICML 2025Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning
  5. ICML 2025Diving into Self-Evolving Training for Multimodal Reasoning
  6. ICML 2025Do NOT Think That Much for 2+3=? On the Overthinking of Long Reasoning Models
  7. ICML 2025DOLPHIN: A Programmable Framework for Scalable Neurosymbolic Learning
  8. ICML 2025DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation
  9. ICML 2025DyCodeEval: Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination
  10. ICML 2025EditLord: Learning Code Transformation Rules for Code Editing
  11. ICML 2025Efficiently Vectorized MCMC on Modern Accelerators
  12. ICML 2025Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models
  13. ICML 2025Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators
  14. ICML 2025Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples
  15. ICML 2025Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning
  16. ICML 2025From Language Models over Tokens to Language Models over Characters
  17. ICML 2025From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
  18. ICML 2025Fully Dynamic Euclidean Bi-Chromatic Matching in Sublinear Update Time
  19. ICML 2025Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
  20. ICML 2025GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation
  21. ICML 2025Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers
  22. ICML 2025GSM-$\infty$: How Do your LLMs Behave over Infinitely Increasing Reasoning Complexity and Context Length?
  23. ICML 2025GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning
  24. ICML 2025How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias
  25. ICML 2025HyperIV: Real-time Implied Volatility Smoothing
  26. ICML 2025HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking
  27. ICML 2025Hypo3D: Exploring Hypothetical Reasoning in 3D
  28. ICML 2025Imagine While Reasoning in Space: Multimodal Visualization-of-Thought
  29. ICML 2025Implicit Language Models are RNNs: Balancing Parallelization and Expressivity
  30. ICML 2025Improving Rationality in the Reasoning Process of Language Models through Self-playing Game
  31. ICML 2025Interchangeable Token Embeddings for Extendable Vocabulary and Alpha-Equivalence
  32. ICML 2025Is Complex Query Answering Really Complex?
  33. ICML 2025IT$^3$: Idempotent Test-Time Training
  34. ICML 2025KernelBench: Can LLMs Write Efficient GPU Kernels?
  35. ICML 2025Large Language Models to Diffusion Finetuning
  36. ICML 2025Latent Thought Models with Variational Bayes Inference-Time Computation
  37. ICML 2025Learning to (Learn at Test Time): RNNs with Expressive Hidden States
  38. ICML 2025Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge
  39. ICML 2025LLMs Can Reason Faster Only If We Let Them
  40. ICML 2025LLMs can see and hear without any training
  41. ICML 2025LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations
  42. ICML 2025Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers
  43. ICML 2025MA-LoT: Model-Collaboration Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving
  44. ICML 2025Machine Learning meets Algebraic Combinatorics: A Suite of Datasets Capturing Research-level Conjecturing Ability in Pure Mathematics
  45. ICML 2025Machines and Mathematical Mutations: Using GNNs to Characterize Quiver Mutation Classes
  46. ICML 2025MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models
  47. ICML 2025MARGE: Improving Math Reasoning with Guided Exploration
  48. ICML 2025MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations
  49. ICML 2025MathConstruct: Challenging LLM Reasoning with Constructive Proofs
  50. ICML 2025Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation

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