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 314 篇，第 1 / 7 页

1. CVPR 20253D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning
2. CVPR 2025Black Swan: Abductive and Defeasible Video Reasoning in Unpredictable Events
3. CVPR 2025Bridging Viewpoint Gaps: Geometric Reasoning Boosts Semantic Correspondence
4. CVPR 2025Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model
5. CVPR 2025Explainable Saliency: Articulating Reasoning with Contextual Prioritization
6. CVPR 2025FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placement
7. CVPR 2025Gromov-Wasserstein Problem with Cyclic Symmetry
8. CVPR 2025Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing
9. CVPR 2025MV-MATH: Evaluating Multimodal Math Reasoning in Multi-Visual Contexts
10. CVPR 2025Perception Tokens Enhance Visual Reasoning in Multimodal Language Models
11. CVPR 2025PRaDA: Projective Radial Distortion Averaging
12. CVPR 2025Reasoning to Attend: Try to Understand How <SEG> Token Works
13. CVPR 2025Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning
14. CVPR 2025SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model
15. CVPR 2025Spatial457: A Diagnostic Benchmark for 6D Spatial Reasoning of Large Mutimodal Models
16. CVPR 2025TSP-Mamba: The Travelling Salesman Problem Meets Mamba for Image Super-resolution and Beyond
17. CVPR 2025VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoning
18. CVPR 2025Visual Agentic AI for Spatial Reasoning with a Dynamic API
19. ICLR 2025Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages
20. ICLR 2025Arithmetic Without Algorithms: Language Models Solve Math with a Bag of Heuristics
21. ICLR 2025B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
22. ICLR 2025Can LLMs Solve Longer Math Word Problems Better?
23. ICLR 2025CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning
24. ICLR 2025Conformal Language Model Reasoning with Coherent Factuality
25. ICLR 2025Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers
26. ICLR 2025Don't Take Things Out of Context: Attention Intervention for Enhancing Chain-of-Thought Reasoning in Large Language Models
27. ICLR 2025DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search
28. ICLR 2025Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces
29. ICLR 2025DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models
30. ICLR 2025From Probability to Counterfactuals: the Increasing Complexity of Satisfiability in Pearl's Causal Hierarchy
31. ICLR 2025G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model
32. ICLR 2025Generalizing Reasoning Problems to Longer Lengths
33. ICLR 2025GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training
34. ICLR 2025GReaTer: Gradients Over Reasoning Makes Smaller Language Models Strong Prompt Optimizers
35. ICLR 2025GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
36. ICLR 2025HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics
37. ICLR 2025Hybrid Regularization Improves Diffusion-based Inverse Problem Solving
38. ICLR 2025Improving Complex Reasoning with Dynamic Prompt Corruption: A Soft Prompt Optimization Approach
39. ICLR 2025Improving Reasoning Performance in Large Language Models via Representation Engineering
40. ICLR 2025INFER: A Neural-symbolic Model For Extrapolation Reasoning on Temporal Knowledge Graph
41. ICLR 2025Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for LLM Problem-Solving
42. ICLR 2025Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist
43. ICLR 2025Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models
44. ICLR 2025LeanAgent: Lifelong Learning for Formal Theorem Proving
45. ICLR 2025Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solving
46. ICLR 2025MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code
47. ICLR 2025MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs
48. ICLR 2025MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine
49. ICLR 2025MIND: Math Informed syNthetic Dialogues for Pretraining LLMs
50. ICLR 2025MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models

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。