ARC: Compiling Hundreds of Requirement Scenarios into A Runnable Web System

TL;DR

ARC is a novel technique that compiles hundreds of requirement scenarios from multi-modal documents into fully runnable web systems, including code, design, tests, and traceability, significantly improving testing success and user productivity.

Contribution

ARC introduces a requirement compilation approach that generates complete, maintainable web systems from multi-modal requirement documents, surpassing existing code generation methods.

Findings

ARC systems pass 50.6% more GUI tests than baselines

Generated systems are maintainable and verifiable

Novice users can produce complex requirement documents in hours

Abstract

Large Language Models (LLMs) have improved programming efficiency, but their performance degrades significantly as requirements scale; when faced with multi-modal documents containing hundreds of scenarios, LLMs often produce incorrect implementations or omit constraints. We propose Agentic Requirement Compilation (ARC), a technique that moves beyond simple code generation to requirement compilation, enabling the creation of runnable web systems directly from multi-modal DSL documents. ARC generates not only source code but also modular designs for UI, API, and database layers, enriched test suites (unit, modular, and integration), and detailed traceability for software maintenance. Our approach employs a bidirectional test-driven agentic loop: a top-down architecture phase decomposes requirements into verifiable interfaces, followed by a bottom-up implementation phase where agents generate code to satisfy those tests. ARC maintains strict traceability across requirements, design, and code to facilitate intelligent asset reuse. We evaluated ARC by generating six runnable web systems from documents spanning 50-200 multi-modal scenarios. Compared to state-of-the-art baselines, ARC-generated systems pass 50.6% more GUI tests on average. A user study with 21 participants showed that novice users can successfully write DSL documents for complex systems, such as a 10K-line ticket-booking system, in an average of 5.6 hours. These results demonstrate that ARC effectively transforms non-trivial requirement specifications into maintainable, runnable software.