# How Stable Are LLM-Generated Proofs Under Program Refactoring? A Stress Test for Verifiable Code Generation

**Published:** October 28, 2026
**Author:** Aravind Mandiga, Guoming Li
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/how-stable-are-llm-generated-proofs-under-program-refactoring-a-stress-t

arXiv:2610.36328v1 Announce Type: new Abstract: Benchmarks for verifiable code generation usually test a proof against one fixed implementation. We ask whether the same proof remains valid after a program refactoring that preserves behavior. We introduce RefactorProof, which…

> From the original source: **arXiv — cs.AI**
> [Read full article at arXiv — cs.AI](https://arxiv.org/abs/2610.36328)

**Tags:** #arXiv #DeepSeek

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*