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

2026-03-16

AI Summary

This work proposes a novel integration of large language models (LLMs) into the Asmeta framework to address the persistent challenge in model-based development wherein users struggle to accurately translate informal requirements into formal temporal logic specifications. The approach establishes a closed-loop, interactive workflow that supports users throughout the definition, formalization, interpretation, and verification of temporal properties, leveraging feedback from model checkers to enable effective human–machine collaboration. By incorporating LLMs as intelligent assistants within this formal methods pipeline, the methodology significantly enhances both the efficiency and accuracy of formal modeling. Empirical validation through representative case studies demonstrates the practical efficacy and promising potential of LLMs in supporting and advancing formal verification tasks.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

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.

Problem

• temporal logic
• formal specification
• model-based development
• requirements formalization

Innovation

• Large Language Models
• Temporal Logic
• Formal Specification
• Model Checking
• Asmeta