Skip to content

A retrieval-augmented LoRA-Tuned LLM framework for structured software test case generation

Oct 2026 · Discover Computing · Vol 29 · 0 citations · 43 references
Software Testing and Debugging Techniques

TL;DR

A novel Retrieval-Augmented and LoRA-tuned Large Language Model is proposed for automated generation of structured software test cases from textual requirements and indicates the potential of retrieval augmentation and parameter-efficient fine-tuning for structured test-case generation within the investigated setting.

Abstract

Modern software systems are becoming increasingly complex that require scalable and reliable testing mechanisms for quality and robustness. The manual test case design remains a significant limitation as it is time-consuming, inconsistent, and prone to human error when dealing with large-scale and evolving requirements. The existing automated models struggle to generate structured, semantically coherent, and contextually relevant test cases which indicates the need for more intelligent and efficient solutions. This study proposes a novel Retrieval-Augmented and LoRA-tuned Large Language Model for automated generation of structured software test cases from textual requirements. The proposed model combines the FLAN-T5 with Retrieval-Augmented Generation to integrate the contextual grounding and Low-Rank Adaptation for parameter-efficient fine-tuning that allows the high-quality generation to maintain the computational efficiency. The proposed model is trained on a large-scale custom dataset that contain real-world test case records collected from enterprise tools such as Jira and Zephyr, and generates structured JSON-based test cases aligned with industrial standards. The enterprise-style structured test-case dataset and controlled experimental protocol used in this study. The proposed configuration achieved a BLEU score of 0.5897, ROUGE-L of 0.8095, BERTScore F1 of 0.9679, and semantic cosine similarity of 0.9816. A duplicate rate of 0.000 and a hallucination rate of 0.017 were also observed under the defined evaluation criteria. The results indicate the potential of retrieval augmentation and parameter-efficient fine-tuning for structured test-case generation within the investigated setting. The enterprise dataset and trained artifacts are restricted and findings interpreted within the scope of the evaluated task rather than as evidence of universal performance superiority. The integration of retrieval augmentation results in a mean inference latency of approximately 6·27s per test case indicates a measurable computational overhead with the improved contextual grounding. The findings show a practical performance between generation quality and inference efficiency within the evaluated enterprise-style test-case generation setting. Not applicable.

Read PDF

Similar papers

#artificial intelligence Preprint Oct 2026

MAP4CS: A Multi-dimensional Data Pruning Framework for Efficient Code Retriever Fine-tuning

Retrieval-Augmented Generation (RAG) has become a cornerstone in software engineering for enhancing Large Language Models (LLMs) with domain-specific knowledge. However, adapting retrievers to evolving code repositories remains challenging due to the noise and redundancy inherent in massive code corpora. Standard fine-...

Yuxuan Chen, Ming-Wei Liu, Guang-Sheng Ou et al. · 0 citations
Oct 2026

Domain-Specific Fine-Tuning of Large Language Models for Retrieval-Augmented Generation in Failure Analysis

Failure Analysis (FA) engineers must diagnose product malfunctions and identify root causes from large volumes of heterogeneous information, including prior debugging procedures and product documentation. This paper examines domain-specific fine-tuning of Large Language Models within a Retrieval-Augmented Generation...

Markus Kofler, Konstantin Schekotihin · 0 citations
#artificial intelligence Conference Open access Sep 2026

Code Comprehensor: Hierarchical Documentation and Cross-Modal Retrieval for Large Repositories

This work proposes Code Comprehensor, a hybrid retrieval-reasoning framework combining CodeGraph, a code dependency callgraph, CodeScribe, which uses code-aware LLMs to generate hierarchical documentation across repository call graphs, and CodeContrast, a CLIP-style dual-encoder model trained on CodeScribe output to le...

Sujoy Roychowdhury, Joseph H. R. Isaac, Jian-Ning Gao et al. · 0 citations
Open access Oct 2026

Implementation and Evaluation of an Efficient RAG System in Resource-Constrained Environments

This work proposes an automatic evaluation pipeline that enables large-scale, reproducible comparison of different configurations by analyzing generated answers and automating the scoring process, and identifies evaluators that best approximate human judgment.

Ernesto Moltó, D. Ruiz, Vanessa Moscardó et al. · 0 citations
Conference Open access Sep 2026

Annotation Light Requirements-to-Test Traceability with Hybrid Retrieval and LLM Validation

Software projects often maintain large requirement and test repositories, yet explicit trace links between them are incomplete or inconsistently maintained. This paper presents a requirements-to-test traceability pipeline that ranks candidate links for natural-language requirements using hybrid retrieval and optional L...

Arda Barış Özten, Eren Tarak, H. Kilinc · 0 citations
Review Open access Oct 2026

A Structured Retrieval Augmented Large Language Model Framework for Automated Engineering Technical Bid Evaluation

In the construction sector, technical bid evaluation is crucial for maintaining equity, evaluating contractor capabilities, and allocating resources efficiently. However, traditional methods rely heavily on manual expert review, which can introduce subjective biases and efficiency bottlenecks. While the existing litera...

Guo-Zong Zhang, Hong-Lin Zhang, Qian-Mai Luo · 0 citations

Related blog posts

Google DeepMind Blog Nov 18, 2026

Genie 4 is now available

We are rolling out a new Project Genie experience to eligible Google AI Ultra subscribers, opening access to our new Genie 4 world model.

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