数学推理论文趋势 2023–2026

定理与解题

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,085 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

数学推理论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20231917111057
202452343912137
2025190614518314
202620817511381577

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

全部数学推理论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 1,085 篇，第 21 / 22 页

  1. NeurIPS 2024Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing
  2. NeurIPS 2024Interpretable Concept-Based Memory Reasoning
  3. NeurIPS 2024JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
  4. NeurIPS 2024Latent Neural Operator for Solving Forward and Inverse PDE Problems
  5. NeurIPS 2024Lean Workbook: A large-scale Lean problem set formalized from natural language math problems
  6. NeurIPS 2024MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems
  7. NeurIPS 2024MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning
  8. NeurIPS 2024MathPile: A Billion-Token-Scale Pretraining Corpus for Math
  9. NeurIPS 2024Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance
  10. NeurIPS 2024Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset
  11. NeurIPS 2024Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
  12. NeurIPS 2024MindMerger: Efficiently Boosting LLM Reasoning in non-English Languages
  13. NeurIPS 2024MLLM-CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs
  14. NeurIPS 2024Neuro-Symbolic Data Generation for Math Reasoning
  15. NeurIPS 2024On the Inductive Bias of Stacking Towards Improving Reasoning
  16. NeurIPS 2024Open-Book Neural Algorithmic Reasoning
  17. NeurIPS 2024OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
  18. NeurIPS 2024Proving Olympiad Algebraic Inequalities without Human Demonstrations
  19. NeurIPS 2024PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition
  20. NeurIPS 2024PUZZLES: A Benchmark for Neural Algorithmic Reasoning
  21. NeurIPS 2024RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold
  22. NeurIPS 2024SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models
  23. NeurIPS 2024SELF-DISCOVER: Large Language Models Self-Compose Reasoning Structures
  24. NeurIPS 2024Solving Inverse Problems via Diffusion Optimal Control
  25. NeurIPS 2024ST$_k$: A Scalable Module for Solving Top-k Problems
  26. NeurIPS 2024StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving
  27. NeurIPS 2024Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
  28. NeurIPS 2024Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought
  29. CVPR 2023Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matrices
  30. CVPR 2023ANetQA: A Large-Scale Benchmark for Fine-Grained Compositional Reasoning Over Untrimmed Videos
  31. CVPR 2023DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network
  32. CVPR 2023Divide and Conquer: Answering Questions With Object Factorization and Compositional Reasoning
  33. CVPR 2023Revisiting the P3P Problem
  34. CVPR 2023Solving 3D Inverse Problems Using Pre-Trained 2D Diffusion Models
  35. CVPR 2023Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective
  36. CVPR 2023Solving Relaxations of MAP-MRF Problems: Combinatorial In-Face Frank-Wolfe Directions
  37. CVPR 2023Super-CLEVR: A Virtual Benchmark To Diagnose Domain Robustness in Visual Reasoning
  38. CVPR 2023Visual Programming: Compositional Visual Reasoning Without Training
  39. ICLR 2023A Stable and Scalable Method for Solving Initial Value PDEs with Neural Networks
  40. ICLR 2023A Unified Algebraic Perspective on Lipschitz Neural Networks
  41. ICLR 2023Complexity-Based Prompting for Multi-step Reasoning
  42. ICLR 2023Differentiable Mathematical Programming for Object-Centric Representation Learning
  43. ICLR 2023Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
  44. ICLR 2023Dual Algorithmic Reasoning
  45. ICLR 2023Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning
  46. ICLR 2023Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought
  47. ICLR 2023Language models are multilingual chain-of-thought reasoners
  48. ICLR 2023Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions
  49. ICLR 2023Learning to Solve Constraint Satisfaction Problems with Recurrent Transformer
  50. ICLR 2023Least-to-Most Prompting Enables Complex Reasoning in Large Language Models

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 查数学推理在 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": "math-reasoning"}

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数学推理论文？
共 1,085 篇，按年份分别是 2023 年 57 篇、2024 年 137 篇、2025 年 314 篇、2026 年 577 篇。
NeurIPS 2026 有多少篇数学推理论文？
NeurIPS 2026 有 208 篇数学推理论文，上一届是 190 篇。
ICLR 2026 有多少篇数学推理论文？
ICLR 2026 有 175 篇数学推理论文，上一届是 61 篇。
ICML 2026 有多少篇数学推理论文？
ICML 2026 有 113 篇数学推理论文，上一届是 45 篇。
CVPR 2026 有多少篇数学推理论文？
CVPR 2026 有 81 篇数学推理论文，上一届是 18 篇。
哪个会议的数学推理论文最多？
NeurIPS，2023–2026 年共 469 篇。

「神经符号」下的其他主题