定理证明论文趋势 2023–2026

主要结论

• 定理证明论文从 2023 年的 3 篇增长到 2026 年的 38 篇，三年间扩大到约 13 倍。
• ICLR 是发定理证明论文最多的会议，2023–2026 年共 32 篇，占四个会议总量的 40%。
• 交叉方向里涨得最快的是数学推理：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 16 篇。
• 在「程序综合」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的形式验证 ML是 3.7 倍，定理证明是 13 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 Theoretical Framework for Self-Play Theorem Proving Algorithms
• ICML 2026Automated Formal Proofs of Combinatorial Identities via Wilf–Zeilberger Guidance and LLMs
• ICLR 2026LoC-Decomp: LLM Autoformalization via Logical Concept Decomposition and Iterative Feedback Correction
• NeurIPS 20253D-Prover: Diversity Driven Theorem Proving With Determinantal Point Processes
• ICML 2025Position: Trustworthy AI Agents Require the Integration of Large Language Models and Formal Methods
• ICLR 2025Alchemy: Amplifying Theorem-Proving Capability Through Symbolic Mutation
• CVPR 2025Automated Proof of Polynomial Inequalities via Reinforcement Learning
• NeurIPS 2024FVEL: Interactive Formal Verification Environment with Large Language Models via Theorem Proving
• ICML 2024Position: The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
• ICLR 2024A Characterization Theorem for Equivariant Networks with Point-wise Activations
• ICML 2023Extending Conformal Prediction to Hidden Markov Models with Exact Validity via de Finetti's Theorem for Markov Chains
• ICLR 2023Formal Mathematics Statement Curriculum Learning
• NeurIPS 2026Compositional Generalization Certificates via the Van Kampen Theorem
• ICML 2026Editable Proof Sketch for Automated Theorem Proving
• ICLR 2026Premise Selection for a Lean Hammer
• NeurIPS 2025Ineq-Comp: Benchmarking Human-Intuitive Compositional Reasoning in Automated Theorem Proving of Inequalities
• ICML 2025ProofAug: Efficient Neural Theorem Proving via Fine-grained Proof Structure Analysis
• ICLR 2025ImProver: Agent-Based Automated Proof Optimization
• NeurIPS 2024Proving Olympiad Algebraic Inequalities without Human Demonstrations
• ICML 2024Subgoal-based Demonstration Learning for Formal Theorem Proving

全部定理证明论文

共 80 篇，第 2 / 2 页

51. NeurIPS 2025ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Data
52. NeurIPS 2025Bootstrapping Hierarchical Autoregressive Formal Reasoner with Chain-of-Proxy-Autoformalization
53. NeurIPS 2025CLEVER: A Curated Benchmark for Formally Verified Code Generation
54. NeurIPS 2025Ineq-Comp: Benchmarking Human-Intuitive Compositional Reasoning in Automated Theorem Proving of Inequalities
55. NeurIPS 2025miniF2F-Lean Revisited: Reviewing Limitations and Charting a Path Forward
56. NeurIPS 2025MPS-Prover: Advancing Stepwise Theorem Proving by Multi-Perspective Search and Data Curation
57. NeurIPS 2025Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models
58. NeurIPS 2025Tree-Based Premise Selection for Lean4
59. ICLR 2024A Characterization Theorem for Equivariant Networks with Point-wise Activations
60. ICLR 2024Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
61. ICLR 2024LEGO-Prover: Neural Theorem Proving with Growing Libraries
62. ICLR 2024Magnushammer: A Transformer-Based Approach to Premise Selection
63. ICLR 2024Mathematical Justification of Hard Negative Mining via Isometric Approximation Theorem
64. ICLR 2024Proving Test Set Contamination in Black-Box Language Models
65. ICLR 2024REFACTOR: Learning to Extract Theorems from Proofs
66. ICLR 2024Where We Have Arrived in Proving the Emergence of Sparse Interaction Primitives in DNNs
67. ICML 2024One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts
68. ICML 2024Position: The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
69. ICML 2024Subgoal-based Demonstration Learning for Formal Theorem Proving
70. NeurIPS 2024Autoformalize Mathematical Statements by Symbolic Equivalence and Semantic Consistency
71. NeurIPS 2024FVEL: Interactive Formal Verification Environment with Large Language Models via Theorem Proving
72. NeurIPS 2024Lean Workbook: A large-scale Lean problem set formalized from natural language math problems
73. NeurIPS 2024Learning Structure-Aware Representations of Dependent Types
74. NeurIPS 2024Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationality
75. NeurIPS 2024Proving Olympiad Algebraic Inequalities without Human Demonstrations
76. NeurIPS 2024Proving Theorems Recursively
77. NeurIPS 2024PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition
78. ICLR 2023Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
79. ICLR 2023Formal Mathematics Statement Curriculum Learning
80. ICML 2023Extending Conformal Prediction to Hidden Markov Models with Exact Validity via de Finetti's Theorem for Markov Chains

常见问题

2023–2026 年四大会议一共有多少篇定理证明论文？

共 80 篇，按年份分别是 2023 年 3 篇、2024 年 19 篇、2025 年 20 篇、2026 年 38 篇。

NeurIPS 2026 有多少篇定理证明论文？

NeurIPS 2026 有 6 篇定理证明论文，上一届是 9 篇。

ICLR 2026 有多少篇定理证明论文？

ICLR 2026 有 15 篇定理证明论文，上一届是 7 篇。

ICML 2026 有多少篇定理证明论文？

ICML 2026 有 17 篇定理证明论文，上一届是 3 篇。

CVPR 2025 有多少篇定理证明论文？

CVPR 2025 有 1 篇定理证明论文。

哪个会议的定理证明论文最多？

ICLR，2023–2026 年共 32 篇。