Pith. sign in

REVIEW 6 cited by

Mathesis: Towards Formal Theorem Proving from Natural Languages

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.07047 v1 pith:HRUDOF67 submitted 2025-06-08 cs.AI

classification cs.AI
keywords formaltheoremgaokao-formallanguagemathesisnaturalproblemsproving
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent advances in large language models show strong promise for formal reasoning. However, most LLM-based theorem provers have long been constrained by the need for expert-written formal statements as inputs, limiting their applicability to real-world problems expressed in natural language. We tackle this gap with Mathesis, the first end-to-end theorem proving pipeline processing informal problem statements. It contributes Mathesis-Autoformalizer, the first autoformalizer using reinforcement learning to enhance the formalization ability of natural language problems, aided by our novel LeanScorer framework for nuanced formalization quality assessment. It also proposes a Mathesis-Prover, which generates formal proofs from the formalized statements. To evaluate the real-world applicability of end-to-end formal theorem proving, we introduce Gaokao-Formal, a benchmark of 488 complex problems from China's national college entrance exam. Our approach is carefully designed, with a thorough study of each component. Experiments demonstrate Mathesis's effectiveness, with the autoformalizer outperforming the best baseline by 22% in pass-rate on Gaokao-Formal. The full system surpasses other model combinations, achieving 64% accuracy on MiniF2F with pass@32 and a state-of-the-art 18% on Gaokao-Formal.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. FormalRx: Rectify and eXamine Semantic Failures in Autoformalization

    cs.CL 2026-07 conditional novelty 7.0 of 10

    FormalRx diagnoses Lean autoformalization failures with a 28-category SCI taxonomy and an 8B model that jointly predicts alignment, error type, location, and correction.

  2. Aria: An Agent For Retrieval and Iterative Auto-Formalization via Dependency Graph

    cs.AI 2025-10 conditional novelty 6.0 of 10

    A graph-of-thought agent with retrieval and a term-grounded semantic checker auto-formalizes research-level math statements in Lean, hitting 68.5% on ProofNet and 6/14 homological conjectures where baselines score 0.

  3. Integrating Rules and Semantics for LLM-Based C-to-Rust Translation

    cs.SE 2025-08 unverdicted novelty 5.0 of 10

    IRENE combines rule-based retrieval, structured summarization, and compiler feedback to improve LLM-based C-to-Rust translation accuracy and safety.

  4. Advocate for Complete Benchmarks for Formal Reasoning with Formal/Informal Statements and Formal/Informal Proofs

    cs.AI 2025-07 conditional novelty 5.0 of 10

    The paper advocates complete four-part benchmarks (formal/informal statements and proofs) for formal reasoning and reports that a published 97% autoformalization accuracy is actually 67% on expert review.

  5. AI for Mathematics: Progress, Challenges, and Prospects

    math.HO 2026-01 unverdicted novelty 4.0 of 10

    AI for math combines task-specific architectures and general foundation models to support research and advance AI reasoning capabilities.

  6. HERMES: Towards Efficient and Verifiable Mathematical Reasoning in LLMs

    cs.AI 2025-11 conditional novelty 4.0 of 10

    Interleaving LLM reasoning with Lean4 verification of individual steps improves math-problem accuracy and cuts token budgets versus reward-model methods.

Pith tools