LLMCFG-TGen: Using LLM-Generated Control Flow Graphs to Automatically Create Test Cases from Use Cases

TL;DR

This paper introduces LLMCFG-TGen, a novel method that leverages large language models to automatically generate comprehensive test cases from natural language use-case descriptions by constructing control flow graphs and exploring all execution paths.

Contribution

The paper presents a new approach combining LLMs and control flow graphs to improve test case completeness and reduce manual effort in requirements-based testing.

Findings

Achieves full path coverage in test generation

Constructs well-structured CFGs from natural language use cases

Reduces manual effort in creating test cases

Abstract

Appropriate test case generation is critical in software testing, significantly impacting the quality of the testing. Requirements-Based Test Generation (RBTG) derives test cases from software requirements, aiming to verify whether or not the system's behaviors align with user needs and expectations. Requirements are often documented in Natural Language (NL), with use-case descriptions being a popular method for capturing functional behaviors and interaction flows in a structured form. Large Language Models (LLMs) have shown strong potential for automating test generation directly from NL requirements. However, current LLM-based approaches may not provide comprehensive, non-redundant coverage. They may also fail to capture complex conditional logic in requirements, resulting in incomplete test cases. We propose a new approach that automatically generates test cases from NL use-case descriptions, called Test Generation based on LLM-generated Control Flow Graphs (LLMCFG-TGen). LLMCFG-TGen comprises three main steps: (1) An LLM transforms a use case into a structured CFG that encapsulates all potential branches; (2) The generated CFG is explored, and all complete execution paths are enumerated; and (3) The execution paths are then used to generate the test cases. To evaluate our proposed approach, we conducted a series of experiments. The results show that LLMs can effectively construct well-structured CFGs from NL use cases. Compared with the baseline methods, LLMCFG-TGen achieves full path coverage, improving completeness and ensuring clear and accurate test cases. Practitioner assessments confirm that LLMCFG-TGen produces logically consistent and comprehensive test cases, while substantially reducing manual effort. The findings suggest that coupling LLM-based semantic reasoning with structured modeling effectively bridges the gap between NL requirements and systematic test generation.