Closed-Loop Multi-Agent Framework for Airborne Systems MBSE Requirements Standardization

Requirements engineering for aerospace systems needs rigorous standards compliance, clarity, and traceability due to stringent safety and reliability criteria. However, existing methods leveraging Large Language Models (LLMs) typically address isolated stages of the requirement engineering process without adequate consideration for compliance standards, closed-loop integration, and iterative optimization. This paper presents an innovative closed-loop multi-agent framework integrating LLMs within the multi-agent platform, specifically designed for aerospace Model-Based Systems Engineering (MBSE). The proposed architecture supports a closed-loop requirement engineering process encompassing requirement extraction, normalization, verification, and optimization. The resulting structured requirements are seamlessly exported to Capella, a leading MBSE modeling tool, ensuring compliance with DO-178C standards.

Authors

Institutions

Publication Details

Published
2025-07-11
DOI
https://doi.org/10.1109/ieeeconf65522.2025.11137286
Primary Topic
Simulation Techniques and Applications
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Closed-Loop Multi-Agent Framework for Airborne Systems MBSE Requirements Standardization

Rui Yuan Wu, Xiaojun Liang, Mingjia Chen, Xiaoning Zhang et al.
Simulation Techniques and Applications
article

Closed-Loop Multi-Agent Framework for Airborne Systems MBSE Requirements Standardization

Rui Yuan Wu, Xiaojun Liang, Mingjia Chen, Xiaoning Zhang, Weichao Luo
article en

Abstract

Requirements engineering for aerospace systems needs rigorous standards compliance, clarity, and traceability due to stringent safety and reliability criteria. However, existing methods leveraging Large Language Models (LLMs) typically address isolated stages of the requirement engineering process without adequate consideration for compliance standards, closed-loop integration, and iterative optimization. This paper presents an innovative closed-loop multi-agent framework integrating LLMs within the multi-agent platform, specifically designed for aerospace Model-Based Systems Engineering (MBSE). The proposed architecture supports a closed-loop requirement engineering process encompassing requirement extraction, normalization, verification, and optimization. The resulting structured requirements are seamlessly exported to Capella, a leading MBSE modeling tool, ensuring compliance with DO-178C standards.

Peng Cheng Laboratory (CN)
Openalex Percentile: Top 72%
Simulation Techniques and Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.