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 190 篇，第 1 / 4 页

1. NeurIPS 20253D-Prover: Diversity Driven Theorem Proving With Determinantal Point Processes
2. NeurIPS 2025A learnability analysis on neuro-symbolic learning
3. NeurIPS 2025A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
4. NeurIPS 2025A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings
5. NeurIPS 2025Absolute Zero: Reinforced Self-play Reasoning with Zero Data
6. NeurIPS 2025AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions
7. NeurIPS 2025Accelerating RL for LLM Reasoning with Optimal Advantage Regression
8. NeurIPS 2025AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning
9. NeurIPS 2025Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
10. NeurIPS 2025Activation-Guided Consensus Merging for Large Language Models
11. NeurIPS 2025Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization
12. NeurIPS 2025AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking
13. NeurIPS 2025Agentic RL Scaling Law: Spontaneous Code Execution for Mathematical Problem Solving
14. NeurIPS 2025Anchored Diffusion Language Model
15. NeurIPS 2025AOR: Anatomical Ontology-Guided Reasoning for Medical Large Multimodal Model in Chest X-Ray Interpretation
16. NeurIPS 2025APOLLO: Automated LLM and Lean Collaboration for Advanced Formal Reasoning
17. NeurIPS 2025Are Language Models Efficient Reasoners? A Perspective from Logic Programming
18. NeurIPS 2025AREAL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning
19. NeurIPS 2025ARM: Adaptive Reasoning Model
20. NeurIPS 2025AtmosSci-Bench: Evaluating the Recent Advance of Large Language Model for Atmospheric Science
21. NeurIPS 2025Atomic Thinking of LLMs: Decoupling and Exploring Mathematical Reasoning Abilities
22. NeurIPS 2025Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models
23. NeurIPS 2025AutoJudge: Judge Decoding Without Manual Annotation
24. NeurIPS 2025AutoOpt: A Dataset and a Unified Framework for Automating Optimization Problem Solving
25. NeurIPS 2025Bag of Tricks for Inference-time Computation of LLM Reasoning
26. NeurIPS 2025Benchmarking Large Language Models with Integer Sequence Generation Tasks
27. NeurIPS 2025Benchmarking Spatiotemporal Reasoning in LLMs and Reasoning Models: Capabilities and Challenges
28. NeurIPS 2025Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations
29. NeurIPS 2025Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
30. NeurIPS 2025Beyond Verifiable Rewards: Scaling Reinforcement Learning in Language Models to Unverifiable Data
31. NeurIPS 2025Bootstrapping Hierarchical Autoregressive Formal Reasoner with Chain-of-Proxy-Autoformalization
32. NeurIPS 2025BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning
33. NeurIPS 2025C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning
34. NeurIPS 2025Can MLLMs Absorb Math Reasoning Abilities from LLMs as Free Lunch?
35. NeurIPS 2025Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning
36. NeurIPS 2025Causal-R: A Causal-Reasoning Geometry Problem Solver for Optimized Solution Exploration
37. NeurIPS 2025Chain of Execution Supervision Promotes General Reasoning in Large Language Models
38. NeurIPS 2025CLAWS:Creativity detection for LLM-generated solutions using Attention Window of Sections
39. NeurIPS 2025Co-PatcheR: Collaborative Software Patching with Component-specific Small Reasoning Models
40. NeurIPS 2025Cognitive Mirrors: Exploring the Diverse Functional Roles of Attention Heads in LLM Reasoning
41. NeurIPS 2025Composing Global Solutions to Reasoning Tasks via Algebraic Objects in Neural Nets
42. NeurIPS 2025Compositional Neural Network Verification via Assume-Guarantee Reasoning
43. NeurIPS 2025Compositional Reasoning with Transformers, RNNs, and Chain of Thought
44. NeurIPS 2025Continuous Thought Machines
45. NeurIPS 2025Contrastive Representations for Temporal Reasoning
46. NeurIPS 2025Controlling Thinking Speed in Reasoning Models
47. NeurIPS 2025Counterfactual reasoning: an analysis of in-context emergence
48. NeurIPS 2025CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models
49. NeurIPS 2025Creativity or Brute Force? Using Brainteasers as a Window into the Problem-Solving Abilities of Large Language Models
50. NeurIPS 2025Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphs

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。