Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ ZENODOarrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Other literature type . 2026
License: CC BY
Data sources: ZENODO
ZENODO
Report . 2026
License: CC BY
Data sources: Datacite
ZENODO
Report . 2026
License: CC BY
Data sources: Datacite
versions View all 2 versions
addClaim

C4AE: A Multi-Agent Engine for Automated C4 Modeling using Google ADK and Parallel Orchestration

Authors: Pagadala, Vamsi Krishna;

C4AE: A Multi-Agent Engine for Automated C4 Modeling using Google ADK and Parallel Orchestration

Abstract

The documentation of software architecture remains a persistent challenge in modern software engineering, characterized by the necessity for clear structural communication and the high operational cost of manual diagram maintenance. The C4 model decomposes systems into hierarchical layers of Context, Container, Component, and Code, emerging as a de facto standard for visualizing architectural abstractions. However, manual production of these artifacts is labor-intensive, errorprone, and suffers from "documentation drift." This paper presents C4AE (C4ArchitectEngine), a novel multi-agent system designed to automate C4 model artifact generation and dynamic sequence diagrams. Built upon the Google Agent Development Kit (ADK) and a Gemini LLM, C4AE introduces a Parallel Orchestration pattern that decouples architectural reasoning into specialized worker agents. These agents execute concurrently within a Parallel Agent construct to maximize throughput and minimize latency, followed by a sequential Merger Agent that synthesizes outputs into semantically coherent architectural definitions. This work details the system's architectural design, ADK framework utilization for state management and agent routing, Mermaid.js implementation as a standardized interchange format, and a hybrid evaluation framework for assessing structural and semantic integrity of LLM-generated software models.

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average