Theorem Proving papers, 2023–2026

Key findings

• Theorem Proving went from 3 papers in 2023 to 38 in 2026, roughly 13x in three years.
• ICLR publishes the most Theorem Proving work: 32 papers from 2023 to 2026, 40% of the four-venue total.
• The fastest-growing overlap is with Mathematical Reasoning: papers tagged with both rose from 1 in 2023 to 16 in 2026.
• Among the 5 topics under Program Synthesis, it ranks #3 by 2026 paper count; the fastest grower in the group, Formal Verification ML, is up 3.7x versus 13x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Theorem Proving papers

24 papers, page 1 of 1

1. ICML 2026A Minimal Agent for Automated Theorem Proving
2. ICML 2026APE-Bench: Evaluating Automated Proof Engineering for Formal Math Libraries
3. ICML 2026Automated Formal Proofs of Combinatorial Identities via Wilf–Zeilberger Guidance and LLMs
4. ICML 2026Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving
5. ICML 2026BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs
6. ICML 2026Can LLMs Reason Like Automated Theorem Provers for Rust Verification? VCoT-Bench: Evaluating via Verification Chain of Thought
7. ICML 2026Compile to Compress: Boosting Formal Theorem Provers by Compiler Outputs
8. ICML 2026Editable Proof Sketch for Automated Theorem Proving
9. ICML 2026Enhancing Neural Theorem Proving via High-Quality Proof Selection and Verifier Feedback
10. ICML 2026Euclean: Automated Geometry Problem Formalization with Unified Verification in Lean
11. ICML 2026Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving
12. ICML 2026From LLM-Generated Conjectures to Lean Formalizations: Automated Polynomial Inequality Proving via Sum-of-Squares Certificates
13. ICML 2026Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing
14. ICML 2026miniF2F-Dafny: LLM-Guided Mathematical Theorem Proving via Auto-Active Verification
15. ICML 2026OptProver: Bridging Olympiad and Optimization through Continual Training in Formal Theorem Proving
16. ICML 2026SorryDB: Can AI Provers Complete Real-World Lean Theorems?
17. ICML 2026Towards Execution-Grounded Automated AI Research
18. ICML 2025MA-LoT: Model-Collaboration Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving
19. ICML 2025Position: Trustworthy AI Agents Require the Integration of Large Language Models and Formal Methods
20. ICML 2025ProofAug: Efficient Neural Theorem Proving via Fine-grained Proof Structure Analysis
21. ICML 2024One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts
22. ICML 2024Position: The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
23. ICML 2024Subgoal-based Demonstration Learning for Formal Theorem Proving
24. ICML 2023Extending Conformal Prediction to Hidden Markov Models with Exact Validity via de Finetti's Theorem for Markov Chains

FAQ

How many Theorem Proving papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

80 in total: 3 in 2023, 19 in 2024, 20 in 2025, 38 in 2026.

How many Theorem Proving papers are at NeurIPS 2026?

NeurIPS 2026 has 6 Theorem Proving papers, versus 9 the year before.

How many Theorem Proving papers are at ICLR 2026?

ICLR 2026 has 15 Theorem Proving papers, versus 7 the year before.

How many Theorem Proving papers are at ICML 2026?

ICML 2026 has 17 Theorem Proving papers, versus 3 the year before.

How many Theorem Proving papers are at CVPR 2025?

CVPR 2025 has 1 Theorem Proving papers.

Which conference publishes the most Theorem Proving papers?

ICLR, with 32 papers from 2023 to 2026.