Saved in:
Bibliographic Details
Main Authors: Wang, Zhongyi, Lin, Tengjie, Chen, Mingshuai, Yang, Mingqi, Li, Haokun, Yi, Xiao, Qin, Shengchao, Yin, Jianwei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.14532
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913998561083392
author Wang, Zhongyi
Lin, Tengjie
Chen, Mingshuai
Yang, Mingqi
Li, Haokun
Yi, Xiao
Qin, Shengchao
Yin, Jianwei
author_facet Wang, Zhongyi
Lin, Tengjie
Chen, Mingshuai
Yang, Mingqi
Li, Haokun
Yi, Xiao
Qin, Shengchao
Yin, Jianwei
contents Fully automated verification of large-scale software and hardware systems is arguably the holy grail of formal methods. Large language models (LLMs) have recently demonstrated their potential for enhancing the degree of automation in formal verification by, e.g., generating formal specifications as essential to deductive verification, yet exhibit poor scalability due to context-length limitations and, more importantly, the difficulty of inferring complex, interprocedural specifications. This paper outlines Preguss - a modular, fine-grained framework for automating the generation and refinement of formal specifications. Preguss synergizes between static analysis and deductive verification by orchestrating two components: (i) potential runtime error (RTE)-guided construction and prioritization of verification units, and (ii) LLM-aided synthesis of interprocedural specifications at the unit level. We envisage that Preguss paves a compelling path towards the automated verification of large-scale programs.
format Preprint
id arxiv_https___arxiv_org_abs_2508_14532
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Preguss: It Analyzes, It Specifies, It Verifies
Wang, Zhongyi
Lin, Tengjie
Chen, Mingshuai
Yang, Mingqi
Li, Haokun
Yi, Xiao
Qin, Shengchao
Yin, Jianwei
Software Engineering
Logic in Computer Science
Fully automated verification of large-scale software and hardware systems is arguably the holy grail of formal methods. Large language models (LLMs) have recently demonstrated their potential for enhancing the degree of automation in formal verification by, e.g., generating formal specifications as essential to deductive verification, yet exhibit poor scalability due to context-length limitations and, more importantly, the difficulty of inferring complex, interprocedural specifications. This paper outlines Preguss - a modular, fine-grained framework for automating the generation and refinement of formal specifications. Preguss synergizes between static analysis and deductive verification by orchestrating two components: (i) potential runtime error (RTE)-guided construction and prioritization of verification units, and (ii) LLM-aided synthesis of interprocedural specifications at the unit level. We envisage that Preguss paves a compelling path towards the automated verification of large-scale programs.
title Preguss: It Analyzes, It Specifies, It Verifies
topic Software Engineering
Logic in Computer Science
url https://arxiv.org/abs/2508.14532