数学推理论文趋势 2023–2026

主要结论

• 数学推理论文从 2023 年的 57 篇增长到 2026 年的 577 篇，三年间扩大到约 10 倍。
• NeurIPS 是发数学推理论文最多的会议，2023–2026 年共 469 篇，占四个会议总量的 43%。
• 交叉方向里涨得最快的是强化学习：同时属于两个主题的论文从 2023 年的 3 篇增至 2026 年的 140 篇。
• 在「神经符号」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的可微推理是 2.5 倍，数学推理是 10 倍。

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

• NeurIPS 2026A mathematical theory of balancing relational generalization and memorization
• ICML 2026ASyMOB: Algebraic Symbolic Mathematical Operations Benchmark
• ICLR 2026AutoGPS: Automated Geometry Problem Solving via Multimodal Formalization and Deductive Reasoning
• CVPR 2026Affine Perspective-Three-Point Problem
• NeurIPS 2025Are Language Models Efficient Reasoners? A Perspective from Logic Programming
• ICML 2025Autoformulation of Mathematical Optimization Models Using LLMs
• ICLR 2025Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages
• CVPR 2025Bridging Viewpoint Gaps: Geometric Reasoning Boosts Semantic Correspondence
• NeurIPS 2024A Careful Examination of Large Language Model Performance on Grade School Arithmetic
• ICML 2024Accelerating Legacy Numerical Solvers by Non-intrusive Gradient-based Meta-solving
• ICLR 2024Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
• CVPR 2024E-GPS: Explainable Geometry Problem Solving via Top-Down Solver and Bottom-Up Generator
• NeurIPS 2023Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning
• ICML 2023Automated Search for Conjectures on Mathematical Constants using Analysis of Integer Sequences
• ICLR 2023Differentiable Mathematical Programming for Object-Centric Representation Learning
• CVPR 2023Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matrices
• NeurIPS 2026A Mechanistic Analysis of Looped Reasoning Language Models
• ICML 2026Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving
• ICLR 2026CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving
• CVPR 2026Hilbert-Geo Solving Solid Geometric Problems by Neural-Symbolic Reasoning

全部数学推理论文

共 34 篇，第 1 / 1 页

1. ICLR 2024Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers
2. ICLR 2024Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models
3. ICLR 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding
4. ICLR 2024Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks
5. ICLR 2024Diffusion Posterior Sampling for Linear Inverse Problem Solving: A Filtering Perspective
6. ICLR 2024Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
7. ICLR 2024Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
8. ICLR 2024Hypothesis Search: Inductive Reasoning with Language Models
9. ICLR 2024Large Language Model Cascades with Mixture of Thought Representations for Cost-Efficient Reasoning
10. ICLR 2024Large Language Models as Analogical Reasoners
11. ICLR 2024Large Language Models Cannot Self-Correct Reasoning Yet
12. ICLR 2024LEGO-Prover: Neural Theorem Proving with Growing Libraries
13. ICLR 2024Let's Verify Step by Step
14. ICLR 2024Llemma: An Open Language Model for Mathematics
15. ICLR 2024Magnushammer: A Transformer-Based Approach to Premise Selection
16. ICLR 2024MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning
17. ICLR 2024MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning
18. ICLR 2024Mathematical Justification of Hard Negative Mining via Isometric Approximation Theorem
19. ICLR 2024MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
20. ICLR 2024MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
21. ICLR 2024MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning
22. ICLR 2024MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data
23. ICLR 2024NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks
24. ICLR 2024On the Markov Property of Neural Algorithmic Reasoning: Analyses and Methods
25. ICLR 2024OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text
26. ICLR 2024Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
27. ICLR 2024REFACTOR: Learning to Extract Theorems from Proofs
28. ICLR 2024SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning
29. ICLR 2024Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
30. ICLR 2024Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency
31. ICLR 2024Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models
32. ICLR 2024THOUGHT PROPAGATION: AN ANALOGICAL APPROACH TO COMPLEX REASONING WITH LARGE LANGUAGE MODELS
33. ICLR 2024ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
34. ICLR 2024When can transformers reason with abstract symbols?

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。