Skip to content

Relationally Guided Use Case Modeling with LLMs

Guang-Yu Wang Bang-Qi Li Ji Wu Zhi-Jun Shao
Sep 2026 · 0 citations
Computer Science

Abstract

Use case flows are important elements of use case modeling because they support downstream software engineering activities, including requirements analysis, architectural and detailed design, and test case generation. However, constructing them manually is costly and expertise-intensive, while existing automated approaches still struggle to preserve semantic consistency, control-flow logic, data-flow logic, and the intended system boundary, especially when identifying branch points and generating alternative flows. To address this problem, we propose FlowGen for complete use case flow construction. FlowGen uses LLM-based Semantic Information Processing (SIP) to extract semantic elements, constructs a Semantic Relational Graph (SRG) encoded by an enhanced R-GAT for basic flow generation (BFGen), and further supports branch point prediction through BPP and branch-conditioned alternative flow generation through AFGen. Evaluations on 13 public and 7 industrial datasets show that FlowGen consistently outperforms competitive baselines in all three core components. In particular, BFGen improves over the best baseline by 14% in Precision, 7-25% in Recall, 11-30% in F1, and 10-19% in AUC; BPP improves Precision by 30-110%, Recall by 33-91%, and F1 by 32-117%; AFGen improves Precision by 8-23%, F1 by 5-18%, and AUC by 0.6-2.5%. Moreover, we validate the effectiveness of the LLM-based SIP module and the attention preservation factor in BFGen, analyze the impact of requirement completeness on BFGen, and examine how different scopes of branch-related context affect AFGen.

View source

Similar papers

Conference Aug 2026

Semantic Tree: Leveraging Semantic UI Representation for Test Case Generation

Software testing is a crucial process in software development. Despite its importance, the software testing process is often time-consuming and inconsistent when performed manually. With the rapid development of Large Language Models (LLMs), software testing processes such as generating test cases have utilized LLMs. N...

Shania Priccilia, Haryono Soeparno, F. L. Gaol et al. · 0 citations
Preprint Aug 2026

Why Do LLMs Fail at OCL Generation? A Graph Reasoning Perspective

The underlying causes of LLM failures in OCL generation are investigated, framing the task as a graph reasoning problem over UML class diagrams and finding that OCL generation performance significantly degrades with increasing navigation depth and structural complexity.

Hamza Attarwala, Moataz Chouchen, Mohammad Hamdaqa et al. · 0 citations
Preprint Sep 2026

KnowFeat: Knowledge-Guided Feature Engineering via LLM Agents

knowFeat, a knowledge-guided feature engineering framework that organizes domain knowledge into five types -- schema metadata, regulatory indicators, detection rules, expert opinions, and court document evidence -- and injects them as structured context into an LLM agent and maintains competitive detection performance...

Chengsong You, Wangyue Li, Wei-Qiao Que et al. · 0 citations
Conference Aug 2026

Evaluating Template- and Model-Guided LLMs for Requirements Specification

Requirements specification is a pivotal activity in software development. The use of structured templates for specifying requirements can improve their clarity, consistency, and analyzability, which is particularly important in safety-critical domains such as avionics to support verification and certification activitie...

Ikram Darif, Zainab Benlagote, Ghizlane El Boussaidi · 1 citation
Open access Sep 2026

Security-Augmented Use Case Flow Refinement for LLM-Based Agentic Systems

Unlike conventional software systems and large language models (LLMs) evaluated in isolation, LLM-based agentic systems introduce a compositional, workflow-level attack surface. Existing security analysis approaches provide limited support for identifying security omissions implicit in functional use case flows and der...

Guang-Yu Wang, Bangqi Li, Ji Wu et al. · 0 citations
Preprint Aug 2026

Towards Automated Domain Model Extraction from Source Code using Heuristics and Open-Source LLMs

This paper proposes an automated approach to extract domain models from source code using lightweight, locally deployable LLMs and achieves high F1-scores on a dataset of ten projects, each comprising a curated domain model and its corresponding implementation, while remaining fully executable on locally deployable LLM...

Alessandra Mancas, Mounir Ammam, Hyacinth Ali et al. · 1 citation

Related blog posts

Microsoft Research Blog Nov 12, 2026

Microsoft Research Focus – Edition #98

What's new in research at Microsoft? Host Anson Ho explores the latest, including AI-powered universal translation, a breakthrough in a 31-year-old mathematics challenge, and advances making AI coding agents faster and more efficient.  The post Microsoft Research Focus – Edition #98 appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.