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 61 / 71 页

  1. NeurIPS 2024MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs
  2. NeurIPS 2024Multi-modal Situated Reasoning in 3D Scenes
  3. NeurIPS 2024MutaPLM: Protein Language Modeling for Mutation Explanation and Engineering
  4. NeurIPS 2024Natural Counterfactuals With Necessary Backtracking
  5. NeurIPS 2024NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples
  6. NeurIPS 2024NeuralSolver: Learning Algorithms For Consistent and Efficient Extrapolation Across General Tasks
  7. NeurIPS 2024Neuro-Symbolic Data Generation for Math Reasoning
  8. NeurIPS 2024Observational Scaling Laws and the Predictability of Langauge Model Performance
  9. NeurIPS 2024OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI
  10. NeurIPS 2024On the Inductive Bias of Stacking Towards Improving Reasoning
  11. NeurIPS 2024On the Power of Decision Trees in Auto-Regressive Language Modeling
  12. NeurIPS 2024One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos
  13. NeurIPS 2024Open-Book Neural Algorithmic Reasoning
  14. NeurIPS 2024OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
  15. NeurIPS 2024PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition
  16. NeurIPS 2024PUZZLES: A Benchmark for Neural Algorithmic Reasoning
  17. NeurIPS 2024ReMI: A Dataset for Reasoning with Multiple Images
  18. NeurIPS 2024ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videos
  19. NeurIPS 2024SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models
  20. NeurIPS 2024SELF-DISCOVER: Large Language Models Self-Compose Reasoning Structures
  21. NeurIPS 2024Self-playing Adversarial Language Game Enhances LLM Reasoning
  22. NeurIPS 2024SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning
  23. NeurIPS 2024SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types
  24. NeurIPS 2024SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation
  25. NeurIPS 2024SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models
  26. NeurIPS 2024Slot State Space Models
  27. NeurIPS 2024SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization
  28. NeurIPS 2024SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors
  29. NeurIPS 2024SpatialRGPT: Grounded Spatial Reasoning in Vision-Language Models
  30. NeurIPS 2024SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers
  31. NeurIPS 2024StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving
  32. NeurIPS 2024TACT: Advancing Complex Aggregative Reasoning with Information Extraction Tools
  33. NeurIPS 2024TopoLogic: An Interpretable Pipeline for Lane Topology Reasoning on Driving Scenes
  34. NeurIPS 2024Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics
  35. NeurIPS 2024Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
  36. NeurIPS 2024Understanding Transformer Reasoning Capabilities via Graph Algorithms
  37. NeurIPS 2024UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
  38. NeurIPS 2024Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought
  39. NeurIPS 2024Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?
  40. NeurIPS 2024Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning
  41. NeurIPS 2024Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models
  42. NeurIPS 2024VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological Images
  43. CVPR 2023A Probabilistic Framework for Lifelong Test-Time Adaptation
  44. CVPR 2023Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matrices
  45. CVPR 2023ActMAD: Activation Matching To Align Distributions for Test-Time-Training
  46. CVPR 2023ANetQA: A Large-Scale Benchmark for Fine-Grained Compositional Reasoning Over Untrimmed Videos
  47. CVPR 2023ConStruct-VL: Data-Free Continual Structured VL Concepts Learning
  48. CVPR 2023Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval
  49. CVPR 2023Discovering the Real Association: Multimodal Causal Reasoning in Video Question Answering
  50. CVPR 2023Divide and Conquer: Answering Questions With Object Factorization and Compositional 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