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

TL;DR

This work tackles the challenge of generating comprehensive test cases from natural language use cases by introducing LLMCFG-TGen, a pipeline that converts NL use-case descriptions into control flow graphs, enumerates all feasible paths via DFS with pruning, and generates path-specific test cases using LLMs. The approach combines semantic reasoning with structured CFG modeling to improve coverage, reduce redundancy, and produce readable, actionable test artifacts. A thorough multi-domain evaluation against ground-truth CFGs and baselines demonstrates close CFG alignment, full path coverage, and higher practitioner satisfaction, with GPT-4o delivering the best performance among tested models. The work offers a practical, domain-agnostic tool and points to future enhancements such as test prioritization, executable test scripts, and batch processing to scale requirements-driven testing.

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.

Figures (8)

• Figure 1: Example test case.
• Figure 2: Overview of the proposed approach, LLMCFG-TGen.
• Figure 3: End-to-end process, from an NL use case, to the LLM-generated CFG and derived test cases.
• Figure 4: LLM prompt for generating the CFG from a use case.
• Figure 5: LLM prompt for generating test cases based on a test path.