WORLDWIDE_SanGuai / Research bulletin

[ worldwide.arakne.de ]

世界很大,讀一小點。

SanGuai 的三日研究佈告板。每天更新,讀完就走。

EST. 202672H上架 72 小時
軟體工程 / 2611.14606

探索架構模型與參考架構之間的關係

Discovering the Relation Between Architectural Models and Reference Architectures

作者: Thi Dinh Tran, Maria Teresa Rossi, Ludovico Iovino, Leonardo Mariani論文發布: 2026-11-13離架倒數: 15 小時

研究速讀

此論文探討如何判斷具體軟體架構是否與其參考架構一致。作者指出通用模型比對演算法在參考架構上並不準確,因而提出基於大型語言模型的流程 RAMD,結合模型分析與結構化提示,並透過迭代式符合性檢查精煉結果。作者在物聯網、自駕與智慧停車三個領域的 64 個開源架構模型上評估,聲稱達到 85.8% 映射準確率。

值得留意

  1. 問題背景:缺乏專用技術時,只能以通用模型比對演算法將架構模型元件映射到參考架構,而作者實驗顯示此法不準確。
  2. 方法:RAMD 是結合模型分析與結構化提示的 LLM 工作流程,並以迭代式參考架構符合性檢查機制精煉結果。
  3. 作者聲稱的結果:在涵蓋三個參考架構的 64 個開源架構模型上,搭配領域知識與 GPT-4o 達到 85.8% 映射準確率,較最強基線高出 44.6 個百分點。

閱讀限制

僅閱讀標題與摘要,未檢視全文,因此無法確認實驗設計、基線選擇、資料集建構與準確率計算方式,也無法驗證作者聲稱的結果。

原始摘要 [EN]

Assessing whether concrete software architectures are consistent with their reference architecture (RA) is essential to ensure that architectural decisions scale coherently across projects, preserving the quality attributes the RA was designed to guarantee. In the absence of dedicated techniques, mapping the components of an architectural model onto a predefined RA can be addressed only with general-purpose model-comparison algorithms. Our experiments show that these algorithms are inaccurate when applied to RAs. To address this gap, we propose Reference Architecture Mapping Discovery (RAMD), an LLM-based workflow that combines model analysis with structured prompting, and refines results through an iterative RA compliance-checking mechanism. We evaluate RAMD on 64 open-source architectural models spanning three RAs from the IoT, self-driving, and smart parking domains. With domain knowledge and GPT-4o, RAMD reaches 85.8% mapping accuracy and outperforms the strongest baseline by 44.6 percentage points, while ensuring structural consistency with the RA.

AI 摘要僅根據公開標題與摘要整理;研究結論來自作者,請以原文為準。