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 52 篇，第 1 / 2 页

  1. NeurIPS 2024A Careful Examination of Large Language Model Performance on Grade School Arithmetic
  2. NeurIPS 2024A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts
  3. NeurIPS 2024Abductive Reasoning in Logical Credal Networks
  4. NeurIPS 2024AlphaMath Almost Zero: Process Supervision without Process
  5. NeurIPS 2024Autoformalize Mathematical Statements by Symbolic Equivalence and Semantic Consistency
  6. NeurIPS 2024AutoPSV: Automated Process-Supervised Verifier
  7. NeurIPS 2024Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
  8. NeurIPS 2024Calibrating Reasoning in Language Models with Internal Consistency
  9. NeurIPS 2024Can Language Models Learn to Skip Steps?
  10. NeurIPS 2024Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?
  11. NeurIPS 2024Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
  12. NeurIPS 2024Chain-of-Thought Reasoning Without Prompting
  13. NeurIPS 2024ClevrSkills: Compositional Language And Visual Reasoning in Robotics
  14. NeurIPS 2024DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving
  15. NeurIPS 2024Decompose, Analyze and Rethink: Solving Intricate Problems with Human-like Reasoning Cycle
  16. NeurIPS 2024Deep Equilibrium Algorithmic Reasoning
  17. NeurIPS 2024Diffusion of Thought: Chain-of-Thought Reasoning in Diffusion Language Models
  18. NeurIPS 2024DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models
  19. NeurIPS 2024Does Reasoning Emerge? Examining the Probabilities of Causation in Large Language Models
  20. NeurIPS 2024Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning
  21. NeurIPS 2024Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning
  22. NeurIPS 2024Evaluating Large Vision-and-Language Models on Children's Mathematical Olympiads
  23. NeurIPS 2024Global Lyapunov functions: a long-standing open problem in mathematics, with symbolic transformers
  24. NeurIPS 2024How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad
  25. NeurIPS 2024Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing
  26. NeurIPS 2024Interpretable Concept-Based Memory Reasoning
  27. NeurIPS 2024JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
  28. NeurIPS 2024Latent Neural Operator for Solving Forward and Inverse PDE Problems
  29. NeurIPS 2024Lean Workbook: A large-scale Lean problem set formalized from natural language math problems
  30. NeurIPS 2024MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems
  31. NeurIPS 2024MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning
  32. NeurIPS 2024MathPile: A Billion-Token-Scale Pretraining Corpus for Math
  33. NeurIPS 2024Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance
  34. NeurIPS 2024Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset
  35. NeurIPS 2024Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
  36. NeurIPS 2024MindMerger: Efficiently Boosting LLM Reasoning in non-English Languages
  37. NeurIPS 2024MLLM-CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs
  38. NeurIPS 2024Neuro-Symbolic Data Generation for Math Reasoning
  39. NeurIPS 2024On the Inductive Bias of Stacking Towards Improving Reasoning
  40. NeurIPS 2024Open-Book Neural Algorithmic Reasoning
  41. NeurIPS 2024OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
  42. NeurIPS 2024Proving Olympiad Algebraic Inequalities without Human Demonstrations
  43. NeurIPS 2024PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition
  44. NeurIPS 2024PUZZLES: A Benchmark for Neural Algorithmic Reasoning
  45. NeurIPS 2024RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold
  46. NeurIPS 2024SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models
  47. NeurIPS 2024SELF-DISCOVER: Large Language Models Self-Compose Reasoning Structures
  48. NeurIPS 2024Solving Inverse Problems via Diffusion Optimal Control
  49. NeurIPS 2024ST$_k$: A Scalable Module for Solving Top-k Problems
  50. NeurIPS 2024StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving

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