Skip to content
Conference

Stepwise PCTL Generation with Closed-Loop Validation for Automated SysML Activity Diagram Verification

Jul 2026 · Annual International Computer Software and Applications Conference · pp. 446-455 · 0 citations · 44 references
Computer Science

Abstract

Converting activity diagrams in System Modeling Language (SysML) and natural language requirements into executable probabilistic verification results remains a key bottleneck for safetycritical model-based systems engineering (MBSE). This process involves the use of probabilistic symbolic models (PRISM) and probabilistic computation tree logic (PCTL) specifications. Existing automation approaches suffer from high error rates due to one-shot generation, lack of intermediate validation, and absence of systematic error recovery. This paper proposes a progressive verification pipeline integrating three synergistic innovations: (1) stepwise PCTL generation decomposes synthesis into validated phases; (2) dual-layer structured intermediate representation separates rule-level validation from model-level validation; (3) closed-loop targeted repair applies type-specific correction strategies. Evaluation on 52 industrial cases across 16 domains demonstrates 92% PCTL accuracy and 92% PRISM equivalence, outperforming state-of-the-art baselines by 7-12 percentage points while reducing verification time by over 90%. Ablation studies confirm synergistic gains across all pipeline components.

View source

Similar papers

Conference Open access Aug 2026

Automated Generation of SysML Activity Diagrams from Industrial Requirements Using LLMs

Evaluated on real-world system-level requirements documents, comprising more than 720 requirements and 72 use cases, the approach generates system-level diagrams comparable to those created by experts and provides valuable architectural recommendations.

Bastian Franze, Dominik Fuchß, Friedrich Wattenberg et al. · 0 citations
Review Open access 2026

Virtual Continuous Testbeds with LLM-Based Test Case Generation: Toward Closed-Loop Validation of Safety-Critical Systems

: This paper presents an automated approach to deriving informal test cases from Requirements Interchange Format (ReqIF)-structured system requirements based on general-purpose Large Language Models (LLMs) with integrated linkage to test evidences based on Digital Dependability Identities (DDIs). Our method enables sce...

Adam Bachorek, Stefan Schwenk, Naveed Akram et al. · 0 citations
Conference Jul 2026

Improving LLM-Based Unit Test Generation Through Root-Cause-Driven Prompt Design

This paper addresses automated unit test generation with large language models (LLMs). LLM-based test generation has not yet attained a quality level sufficient for practical use in industry. Although LLMs often reproduce API syntax faithfully, they frequently disregard semantic usage constraints and execution-environm...

Mizuki Yamada, Masahiko Kato, Juichi Takahashi · 0 citations
Conference Aug 2026

LLM-Driven Low-Code Task Orchestration for Agile Flexible Manufacturing in Mass Customization

Mass customization demands manufacturing systems that can rapidly reconfigure production workflows for diverse product variants. Traditional robot task programming requires specialized engineers and hours of manual coding, which slows agile changeover. We present a low-code task orchestration platform that uses large l...

Yanping Deng, Jinze Yu · 0 citations
Open access Sep 2026

Model‐Based Formal Verification of Mode Transition Logic in Safety‐Critical Avionics

The proposed FMSysML, a SysML‐based profile that captures the structural and behavioral semantics of flight modes and enforces static semantic consistency rules, enables scalable, traceable, and practical formal verification of safety‐critical flight mode transitions.

Heng Xu, Zhi-Qiu Huang, Fan Shi et al. · 0 citations
Open access Aug 2026

Toward generalizable unified modeling language automation: a dual case study on class and use case diagram generation

A dual-LLM pipeline integrating lightweight specification generation with reasoning-oriented code synthesis is presented, establishing a robust foundation for scalable, artificial intelligence-driven automation in software engineering.

Van-Viet Nguyen, Huu-Khanh Nguyen, Kim-Son Nguyen et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.