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 19 / 22 页

  1. CVPR 2024Synthesize Step-by-Step: Tools Templates and LLMs as Data Generators for Reasoning-Based Chart VQA
  2. CVPR 2024Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models
  3. CVPR 2024What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models
  4. ICLR 2024Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers
  5. ICLR 2024Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models
  6. ICLR 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding
  7. ICLR 2024Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks
  8. ICLR 2024Diffusion Posterior Sampling for Linear Inverse Problem Solving: A Filtering Perspective
  9. ICLR 2024Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
  10. ICLR 2024Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
  11. ICLR 2024Hypothesis Search: Inductive Reasoning with Language Models
  12. ICLR 2024Large Language Model Cascades with Mixture of Thought Representations for Cost-Efficient Reasoning
  13. ICLR 2024Large Language Models as Analogical Reasoners
  14. ICLR 2024Large Language Models Cannot Self-Correct Reasoning Yet
  15. ICLR 2024LEGO-Prover: Neural Theorem Proving with Growing Libraries
  16. ICLR 2024Let's Verify Step by Step
  17. ICLR 2024Llemma: An Open Language Model for Mathematics
  18. ICLR 2024Magnushammer: A Transformer-Based Approach to Premise Selection
  19. ICLR 2024MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning
  20. ICLR 2024MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning
  21. ICLR 2024Mathematical Justification of Hard Negative Mining via Isometric Approximation Theorem
  22. ICLR 2024MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
  23. ICLR 2024MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
  24. ICLR 2024MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning
  25. ICLR 2024MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data
  26. ICLR 2024NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks
  27. ICLR 2024On the Markov Property of Neural Algorithmic Reasoning: Analyses and Methods
  28. ICLR 2024OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text
  29. ICLR 2024Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
  30. ICLR 2024REFACTOR: Learning to Extract Theorems from Proofs
  31. ICLR 2024SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning
  32. ICLR 2024Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
  33. ICLR 2024Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency
  34. ICLR 2024Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models
  35. ICLR 2024THOUGHT PROPAGATION: AN ANALOGICAL APPROACH TO COMPLEX REASONING WITH LARGE LANGUAGE MODELS
  36. ICLR 2024ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
  37. ICLR 2024When can transformers reason with abstract symbols?
  38. ICML 2024A Neural-Guided Dynamic Symbolic Network for Exploring Mathematical Expressions from Data
  39. ICML 2024Accelerating Legacy Numerical Solvers by Non-intrusive Gradient-based Meta-solving
  40. ICML 2024Ambiguity-Aware Abductive Learning
  41. ICML 2024Analysis for Abductive Learning and Neural-Symbolic Reasoning Shortcuts
  42. ICML 2024Attention Meets Post-hoc Interpretability: A Mathematical Perspective
  43. ICML 2024Auto-Regressive Next-Token Predictors are Universal Learners
  44. ICML 2024Case-Based or Rule-Based: How Do Transformers Do the Math?
  45. ICML 2024ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimodal Models
  46. ICML 2024ContPhy: Continuum Physical Concept Learning and Reasoning from Videos
  47. ICML 2024Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training
  48. ICML 2024CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution
  49. ICML 2024Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?
  50. ICML 2024Enforcing Constraints in RNA Secondary Structure Predictions: A Post-Processing Framework Based on the Assignment Problem

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