TDD Governance for Multi-Agent Code Generation via Prompt Engineering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hasanli, Tarlan, Siddeeq, Shahbaz, Khanal, Bishwash, Kotilainen, Pyry, Mikkonen, Tommi, Abrahamsson, Pekka
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909000758460416
author Hasanli, Tarlan
Siddeeq, Shahbaz
Khanal, Bishwash
Kotilainen, Pyry
Mikkonen, Tommi
Abrahamsson, Pekka
author_facet Hasanli, Tarlan
Siddeeq, Shahbaz
Khanal, Bishwash
Kotilainen, Pyry
Mikkonen, Tommi
Abrahamsson, Pekka
contents Large language models (LLMs) accelerate software development but often exhibit instability, non-determinism, and weak adherence to development discipline in unconstrained workflows. While test-driven development (TDD) provides a structured Red-Green-Refactor process, existing LLM-based approaches typically use tests as auxiliary inputs rather than enforceable process constraints. We present an AI-native TDD framework that operationalizes classical TDD principles as structured prompt-level and workflow-level governance mechanisms. Extracted principles are formalized in a machine-readable manifesto and distributed across planning, generation, repair, and validation stages within a layered architecture that separates model proposal from deterministic engine authority. The system enforces phase ordering, bounded repair loops, validation gates, and atomic mutation control to improve stability and reproducibility. We describe architecture and discuss encoding software engineering discipline directly into prompt orchestration, which we think offers a promising direction for reliable LLM-assisted development.
format Preprint
id arxiv_https___arxiv_org_abs_2604_26615
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TDD Governance for Multi-Agent Code Generation via Prompt Engineering
Hasanli, Tarlan
Siddeeq, Shahbaz
Khanal, Bishwash
Kotilainen, Pyry
Mikkonen, Tommi
Abrahamsson, Pekka
Software Engineering
Artificial Intelligence
Large language models (LLMs) accelerate software development but often exhibit instability, non-determinism, and weak adherence to development discipline in unconstrained workflows. While test-driven development (TDD) provides a structured Red-Green-Refactor process, existing LLM-based approaches typically use tests as auxiliary inputs rather than enforceable process constraints. We present an AI-native TDD framework that operationalizes classical TDD principles as structured prompt-level and workflow-level governance mechanisms. Extracted principles are formalized in a machine-readable manifesto and distributed across planning, generation, repair, and validation stages within a layered architecture that separates model proposal from deterministic engine authority. The system enforces phase ordering, bounded repair loops, validation gates, and atomic mutation control to improve stability and reproducibility. We describe architecture and discuss encoding software engineering discipline directly into prompt orchestration, which we think offers a promising direction for reliable LLM-assisted development.
title TDD Governance for Multi-Agent Code Generation via Prompt Engineering
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2604.26615