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 996 篇，第 18 / 20 页

  1. ICLR 2025VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning
  2. ICLR 2025Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations
  3. ICLR 2025What Makes a Maze Look Like a Maze?
  4. ICLR 2025What Makes Large Language Models Reason in (Multi-Turn) Code Generation?
  5. ICLR 2025When does compositional structure yield compositional generalization? A kernel theory.
  6. ICLR 2024Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers
  7. ICLR 2024Active Test-Time Adaptation: Theoretical Analyses and An Algorithm
  8. ICLR 2024AgentBench: Evaluating LLMs as Agents
  9. ICLR 2024Amortizing intractable inference in large language models
  10. ICLR 2024Are Human-generated Demonstrations Necessary for In-context Learning?
  11. ICLR 2024At Which Training Stage Does Code Data Help LLMs Reasoning?
  12. ICLR 2024BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
  13. ICLR 2024Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs
  14. ICLR 2024Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World
  15. ICLR 2024Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models
  16. ICLR 2024Can Large Language Models Infer Causation from Correlation?
  17. ICLR 2024Causal Modelling Agents: Causal Graph Discovery through Synergising Metadata- and Data-driven Reasoning
  18. ICLR 2024Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources
  19. ICLR 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding
  20. ICLR 2024CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules
  21. ICLR 2024COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits
  22. ICLR 2024CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models
  23. ICLR 2024Continual Momentum Filtering on Parameter Space for Online Test-time Adaptation
  24. ICLR 2024CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets
  25. ICLR 2024Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
  26. ICLR 2024DQ-LoRe: Dual Queries with Low Rank Approximation Re-ranking for In-Context Learning
  27. ICLR 2024DSPy: Compiling Declarative Language Model Calls into State-of-the-Art Pipelines
  28. ICLR 2024DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks
  29. ICLR 2024Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors
  30. ICLR 2024Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
  31. ICLR 2024GENOME: Generative Neuro-Symbolic Visual Reasoning by Growing and Reusing Modules
  32. ICLR 2024Hypothesis Search: Inductive Reasoning with Language Models
  33. ICLR 2024I-PHYRE: Interactive Physical Reasoning
  34. ICLR 2024LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving
  35. ICLR 2024Large Language Model Cascades with Mixture of Thought Representations for Cost-Efficient Reasoning
  36. ICLR 2024Large Language Models as Analogical Reasoners
  37. ICLR 2024Large Language Models Cannot Self-Correct Reasoning Yet
  38. ICLR 2024Learning Performance-Improving Code Edits
  39. ICLR 2024Lemur: Harmonizing Natural Language and Code for Language Agents
  40. ICLR 2024Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs
  41. ICLR 2024Let's Verify Step by Step
  42. ICLR 2024LLCP: Learning Latent Causal Processes for Reasoning-based Video Question Answer
  43. ICLR 2024Llemma: An Open Language Model for Mathematics
  44. ICLR 2024Look, Remember and Reason: Grounded Reasoning in Videos with Language Models
  45. ICLR 2024Magnushammer: A Transformer-Based Approach to Premise Selection
  46. ICLR 2024MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning
  47. ICLR 2024MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
  48. ICLR 2024MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
  49. ICLR 2024MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning
  50. ICLR 2024MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data

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