Formalizing and validating properties in Asmeta with Large Language Models (Extended Abstract)

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Bombarda, Andrea, Bonfanti, Silvia, Gargantini, Angelo, Pellegrinelli, Nico
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910054769229824
author Bombarda, Andrea
Bonfanti, Silvia
Gargantini, Angelo
Pellegrinelli, Nico
author_facet Bombarda, Andrea
Bonfanti, Silvia
Gargantini, Angelo
Pellegrinelli, Nico
contents Writing temporal logic properties is often a challenging task for users of model-based development frameworks, particularly when translating informal requirements into formal specifications. In this paper, we explore the idea of integrating Large Language Models (LLMs) into the Asmeta framework to assist users during the definition, formalization, explanation, and validation of temporal properties. We present a workflow in which an LLM-based agent supports these activities by leveraging the Asmeta specification and the feedback produced by the model checker. This work serves as a proof of concept that illustrates the feasibility and potential benefits of such an integration through representative examples.
format Preprint
id arxiv_https___arxiv_org_abs_2603_15375
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Formalizing and validating properties in Asmeta with Large Language Models (Extended Abstract)
Bombarda, Andrea
Bonfanti, Silvia
Gargantini, Angelo
Pellegrinelli, Nico
Software Engineering
Writing temporal logic properties is often a challenging task for users of model-based development frameworks, particularly when translating informal requirements into formal specifications. In this paper, we explore the idea of integrating Large Language Models (LLMs) into the Asmeta framework to assist users during the definition, formalization, explanation, and validation of temporal properties. We present a workflow in which an LLM-based agent supports these activities by leveraging the Asmeta specification and the feedback produced by the model checker. This work serves as a proof of concept that illustrates the feasibility and potential benefits of such an integration through representative examples.
title Formalizing and validating properties in Asmeta with Large Language Models (Extended Abstract)
topic Software Engineering
url https://arxiv.org/abs/2603.15375