Architecture Without Architects: How AI Coding Agents Shape Software Architecture

• URL: http://arxiv.org/abs/2604.04990v1
• Date: Sun, 05 Apr 2026 07:32:37 GMT
• Title: Architecture Without Architects: How AI Coding Agents Shape Software Architecture
• Abstract summary: We propose six prompt-architecture coupling patterns to map natural-structured prompt features to the infrastructure they require.<n>We term the phenomenon vibe architecting, architecture shaped by prompts rather than deliberate design, and outline review practices, decision records, and tooling to bring these hidden decisions under governance.
• Score: 0.6299766708197881
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: AI coding agents select frameworks, scaffold infrastructure, and wire integrations, often in seconds. These are architectural decisions, yet almost no one reviews them as such. We identify five mechanisms by which agents make implicit architectural choices and propose six prompt-architecture coupling patterns that map natural-language prompt features to the infrastructure they require. The patterns range from contingent couplings (structured output validation) that may weaken as models improve to fundamental ones (tool-call orchestration) that persist regardless of model capability. An illustrative demonstration confirms that prompt wording alone produces structurally different systems for the same task. We term the phenomenon vibe architecting, architecture shaped by prompts rather than deliberate design, and outline review practices, decision records, and tooling to bring these hidden decisions under governance.

Related papers

• Agentic Designer: Progressive Multi-Agent Collaboration for Structure-Aware Interior Layout Generation [84.5255199507027]
  Agentic Designer is a progressive framework that formulates structure-aware interior layout generation as an iterative and constraint-verified decision process.<n>By layout decomposing into modular stages of proposal, verification, synthesis and adjustment, the framework coordinates three specialized agents, a Generator, an Evaluator, and a Refiner.<n>This mechanism enforces stepwise geometric validation and correction before each placement is committed, thereby preventing error accumulation.
  arXiv  Detail & Related papers  (2026-07-23T02:46:11Z)
• Bridging Requirements and Architecture: Multi-Agent Orchestration with External Knowledge and Hierarchical Memory [37.071260774880884]
  We propose MAAD (Multi-Agent Architecture Design), a knowledge-driven framework that orchestrates four specialized agents to attribute architectural blueprints.<n>We show that MAAD generates more complete, modular, and traceable architectures than the baseline, and its dedicated Evaluator agent autonomously produces structured quality evaluation reports.
  arXiv  Detail & Related papers  (2026-05-31T18:18:31Z)
• A Pattern Language for Resilient Visual Agents [69.08074737002393]
  We propose an architectural pattern language for visual agents that separates fast, deterministic reflexes from slow, probabilistic supervision.<n>It consists of four architectural design patterns: (1) Hybrid Affordance Integration, (2) Adaptive Visual Anchoring, (3) Visual Hierarchy Synthesis, and (4) Semantic Scene Graph.
  arXiv  Detail & Related papers  (2026-04-30T15:24:26Z)
• Architectural Design Decisions in AI Agent Harnesses [1.8222732878503212]
  This paper presents a protocol-guided, source-grounded empirical study of 70 publicly available agent-system projects.<n>We identify five recurring design dimensions (subagent architecture, context management, tool systems, safety mechanisms, and orchestration) and find that the corpus favors file-persistent, hybrid, and hierarchical context strategies.<n>We synthesize five recurring architectural patterns spanning lightweight tools, balanced CLI frameworks, multi-agent orchestrators, enterprise systems, and scenario-verticalized projects.
  arXiv  Detail & Related papers  (2026-04-20T10:39:34Z)
• Unified Architecture Metamodel of Information Systems Developed by Generative AI [0.0]
  This study explores the problem of creating a unified architecture for LLM-oriented applications based on selected architectural frameworks by SMEs.<n>A framework structure is proposed that covers some key types of architectural diagrams and supports a closed cycle of transformations.<n>The conducted experiments demonstrated the stable quality of generated documentation and code when using a structured architectural context in the form of architectural diagrams.
  arXiv  Detail & Related papers  (2026-03-31T19:22:15Z)
• A Two-Dimensional Framework for AI Agent Design Patterns: Cognitive Function and Execution Topology [54.72352855252792]
  We propose a two-dimensional classification that combines a Cognitive Function axis with seven categories and an Execution Topology axis with six structural archetypes.<n>The resulting 7x6 matrix identifies 27 named patterns, 13 with original names and provides a principled, framework-neutral, and model-agnostic vocabulary for AI agent architecture design.
  arXiv  Detail & Related papers  (2026-03-16T04:01:01Z)
• Architecture-Aware Multi-Design Generation for Repository-Level Feature Addition [53.50448142467294]
  RAIM is a multi-design and architecture-aware framework for repository-level feature addition.<n>It shifts away from linear patching by generating multiple diverse implementation designs.<n>Experiments on the NoCode-bench Verified dataset demonstrate that RAIM establishes a new state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-03-02T12:50:40Z)
• Agentic Design Patterns: A System-Theoretic Framework [8.108572809924956]
  Existing efforts to agentic design patterns often lack a rigorous systems-theoretic foundation.<n>We propose a novel system-theoretic framework that deconstructs an agentic AI system into five core, interacting functional subsystems.<n>We present a collection of 12 agentic design patterns that offer reusable, structural solutions to recurring problems in agent design.
  arXiv  Detail & Related papers  (2026-01-27T16:14:08Z)
• Neurosymbolic Architectural Reasoning: Towards Formal Analysis through Neural Software Architecture Inference [4.023600998747813]
  We outline neural architecture inference to solve the problem of having a formal architecture definition for subsequent symbolic reasoning over these architectures.<n>We discuss how this approach works in general and outline a research agenda based on six general research question that need to be addressed.
  arXiv  Detail & Related papers  (2025-03-20T15:56:54Z)
• Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning [50.47568731994238]
  Key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL) This paper presents a general framework model for integrating and learning structured reasoning into AI agents' policies.
  arXiv  Detail & Related papers  (2023-12-22T17:57:57Z)
• Towards Responsible Generative AI: A Reference Architecture for Designing Foundation Model based Agents [28.406492378232695]
  Foundation model based agents derive their autonomy from the capabilities of foundation models. This paper presents a pattern-oriented reference architecture that serves as guidance when designing foundation model based agents.
  arXiv  Detail & Related papers  (2023-11-22T04:21:47Z)
• Enhancing Architecture Frameworks by Including Modern Stakeholders and their Views/Viewpoints [48.87872564630711]
  The stakeholders with data science and Machine Learning related concerns, such as data scientists and data engineers, are yet to be included in existing architecture frameworks.<n>We surveyed 61 subject matter experts from over 25 organizations in 10 countries.
  arXiv  Detail & Related papers  (2023-08-09T21:54:34Z)
• A Compositional Approach to Creating Architecture Frameworks with an Application to Distributed AI Systems [16.690434072032176]
  We show how compositional thinking can provide rules for the creation and management of architectural frameworks for complex systems. The aim of the paper is not to provide viewpoints or architecture models specific to AI systems, but instead to provide guidelines on how a consistent framework can be built up with existing, or newly created, viewpoints.
  arXiv  Detail & Related papers  (2022-12-27T18:05:02Z)
• Federated Learning with Heterogeneous Architectures using Graph HyperNetworks [154.60662664160333]
  We propose a new FL framework that accommodates heterogeneous client architecture by adopting a graph hypernetwork for parameter sharing. Unlike existing solutions, our framework does not limit the clients to share the same architecture type, makes no use of external data and does not require clients to disclose their model architecture.
  arXiv  Detail & Related papers  (2022-01-20T21:36:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.