RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems

2026-03-30 · Oliver Aleksander Larsen, Mahyar T. Moghaddam arxiv

AI-augmented ecosystems (interconnected systems where multiple AI components interact through shared data and infrastructure) are becoming the architectural norm for smart cities, autonomous fleets, and intelligent platforms. Yet the architecture documentation frameworks practitioners rely on, arc42 and the C4 model, were designed for deterministic software and cannot capture probabilistic behavior, data-dependent evolution, or dual ML/software lifecycles. This gap carries regulatory consequence: the EU AI Act (Regulation 2024/1689) mandates technical documentation through Annex IV that no existing framework provides structured support for, with enforcement for high-risk systems beginning August 2, 2026. We present RAD-AI, a backward-compatible extension framework that augments arc42 with eight AI-specific sections and C4 with three diagram extensions, complemented by a systematic EU AI Act Annex IV compliance mapping. A regulatory coverage assessment with six experienced software-architecture practitioners provides preliminary evidence that RAD-AI increases Annex IV addressability from approximately 36% to 93% (mean rating) and demonstrates substantial improvement over existing frameworks. Comparative analysis on two production AI platforms (Uber Michelangelo, Netflix Metaflow) captures eight additional AI-specific concerns missed by standard frameworks and demonstrates that documentation deficiencies are structural rather than domain-specific. An illustrative smart mobility ecosystem case study reveals ecosystem-level concerns, including cascading drift and differentiated compliance obligations, that are invisible under standard notation.

📄 PDF Abstract BibTeX arXiv:2603.28735

Code (0)

등록된 구현이 없습니다.

AI Assistants to Enhance and Exploit the PETSc Knowledge Base

2025-06-25 · Barry Smith, Junchao Zhang, Hong Zhang, Lois Curfman McInnes 외

Generative AI, especially through large language models (LLMs), is transforming how technical knowledge can be accessed, reused, and extended. PETSc, a widely used numerical library for high-performance scientific comput…

RAG Reranking Retrieval-augmented Generation scientific discovery

Contract2Tool: Learning Preconditions and Effects for Reliable Tool-Augmented LLM Agents

2026-06-05 · Rahul Suresh Babu, Laxmipriya Ganesh Iyer arxiv

Tool-augmented large language model agents increasingly rely on external APIs, but standard tool schemas describe how to call a tool, not when the tool is causally appropriate or what task state it produces. Causal tool …

Enhancing Scientific Reproducibility Through Automated BioCompute Object Creation Using Retrieval-Augmented Generation from Publications

2024-09-23 · Sean Kim, Raja Mazumder

The exponential growth in computational power and accessibility has transformed the complexity and scale of bioinformatics research, necessitating standardized documentation for transparency, reproducibility, and regulat…

Hallucination Long-Context Understanding RAG Re-Ranking+2

Building A Coding Assistant via the Retrieval-Augmented Language Model

2024-10-21 · Xinze Li, Hanbin Wang, Zhenghao Liu, Shi Yu 외

Pretrained language models have shown strong effectiveness in code-related tasks, such as code retrieval, code generation, code summarization, and code completion tasks. In this paper, we propose COde assistaNt viA retri…

Code Completion Code Generation Code Summarization Language Modeling+3

Generation-Augmented Query Expansion For Code Retrieval

2022-12-20 · Dong Li, Yelong Shen, Ruoming Jin, Yi Mao 외

Pre-trained language models have achieved promising success in code retrieval tasks, where a natural language documentation query is given to find the most relevant existing code snippet. However, existing models focus o…

Code Generation Retrieval