Cover Image

Why Agentic Theorem Prover Works: A Statistical Provability Theory of Mathematical Reasoning Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sonoda, Sho, Akiyama, Shunta, Uezato, Yuya
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Exponential Sample Complexity Separation between Flat and Hierarchical Agentic Theorem Provers
by: Sonoda, Sho, et al.
Published: (2026)

Block Coordinate Descent for Neural Networks Provably Finds Global Minima
by: Akiyama, Shunta
Published: (2025)

REAL-Prover: Retrieval Augmented Lean Prover for Mathematical Reasoning
by: Shen, Ziju, et al.
Published: (2025)

Why and When Deep is Better than Shallow: Implementation-Agnostic State-Transition Model of Deep Learning
by: Sonoda, Sho, et al.
Published: (2025)

Deep Ridgelet Transform and Unified Universality Theorem for Deep and Shallow Joint-Group-Equivariant Machines
by: Sonoda, Sho, et al.
Published: (2024)

Generalization Error Bounds for Picard-Type Operator Learning in Nonlinear Parabolic PDEs
by: Taniguchi, Koichi, et al.
Published: (2026)

Why High-rank Neural Networks Generalize?: An Algebraic Framework with RKHSs
by: Hashimoto, Yuka, et al.
Published: (2025)

PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition
by: Tsoukalas, George, et al.
Published: (2024)

A unified Fourier slice method to derive ridgelet transform for a variety of depth-2 neural networks
by: Sonoda, Sho, et al.
Published: (2024)

Goedel-Prover: A Frontier Model for Open-Source Automated Theorem Proving
by: Lin, Yong, et al.
Published: (2025)

Discovering New Theorems via LLMs with In-Context Proof Learning in Lean
by: Kasaura, Kazumi, et al.
Published: (2025)

Regular Expressions with Backreferences and Lookaheads Capture NLOG
by: Uezato, Yuya
Published: (2024)

Prover Agent: An Agent-Based Framework for Formal Mathematical Proofs
by: Baba, Kaito, et al.
Published: (2025)

Provable Statistical Rates for Consistency Diffusion Models
by: Dou, Zehao, et al.
Published: (2024)

SorryDB: Can AI Provers Complete Real-World Lean Theorems?
by: Letson, Austin, et al.
Published: (2026)

Winning Lottery Tickets in Neural Networks via a Quantum-Inspired Classical Algorithm
by: Isogai, Natsuto, et al.
Published: (2026)

OptProver: Bridging Olympiad and Optimization through Continual Training in Formal Theorem Proving
by: Li, Chenyi, et al.
Published: (2026)

STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving
by: Dong, Kefan, et al.
Published: (2025)

Compile to Compress: Boosting Formal Theorem Provers by Compiler Outputs
by: Li, Guchan, et al.
Published: (2026)

Can LLMs Reason Like Automated Theorem Provers for Rust Verification? VCoT-Bench: Evaluating via Verification Chain of Thought
by: Xie, Zichen, et al.
Published: (2026)

Ax-Prover: A Deep Reasoning Agentic Framework for Theorem Proving in Mathematics and Quantum Physics
by: Breen, Benjamin, et al.
Published: (2025)

Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction
by: Lin, Yong, et al.
Published: (2025)

Koopman-based generalization bound: New aspect for full-rank weights
by: Hashimoto, Yuka, et al.
Published: (2023)

Model-agnostic Selective Labeling with Provable Statistical Guarantees
by: Huang, Huipeng, et al.
Published: (2025)

TaoBench: Do Automated Theorem Prover LLMs Generalize Beyond MathLib?
by: Taylor, Alexander K, et al.
Published: (2026)

Memorize Theorems, Not Instances: Probing SFT Generalization through Mathematical Reasoning
by: Peng, Ruiying, et al.
Published: (2026)

Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation
by: Cha, Sungmin, et al.
Published: (2025)

Generative Autoencoding of Dropout Patterns
by: Maeda, Shunta
Published: (2023)

Lean Formalization of Generalization Error Bound by Rademacher Complexity and Dudley's Entropy Integral
by: Sonoda, Sho, et al.
Published: (2025)

When and Why Does Unsupervised RL Succeed in Mathematical Reasoning? A Manifold Envelopment Perspective
by: Zhang, Zelin, et al.
Published: (2026)

On the Complexity of the Matching Problem of Regular Expressions with Backreferences
by: Kumabe, Soh, et al.
Published: (2026)

On the Provable Performance Guarantee of Efficient Reasoning Models
by: Zeng, Hao, et al.
Published: (2025)

Towards Better Search with Domain-Aware Text Embeddings for C2C Marketplaces
by: Rusli, Andre, et al.
Published: (2025)

Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum
by: Rajaraman, Nived, et al.
Published: (2026)

A Hierarchical Language Model with Predictable Scaling Laws and Provable Benefits of Reasoning
by: Gaitonde, Jason, et al.
Published: (2026)

Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training
by: Bu, Dake, et al.
Published: (2025)

The Library Theorem: How External Organization Governs Agentic Reasoning Capacity
by: Mainen, Zachary F.
Published: (2026)

Agentic Transformers Provably Learn to Search via Reinforcement Learning
by: Yang, Tong, et al.
Published: (2026)

Why Does Agentic Safety Fail to Generalize Across Tasks?
by: Slutzky, Yonatan, et al.
Published: (2026)

A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees
by: Kitamura, Toshinori, et al.
Published: (2024)