Understanding LLM-Driven Test Oracle Generation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bodicoat, Adam, Jahangirova, Gunel, Terragni, Valerio
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915718416564224
author Bodicoat, Adam
Jahangirova, Gunel
Terragni, Valerio
author_facet Bodicoat, Adam
Jahangirova, Gunel
Terragni, Valerio
contents Automated unit test generation aims to improve software quality while reducing the time and effort required for creating tests manually. However, existing techniques primarily generate regression oracles that predicate on the implemented behavior of the class under test. They do not address the oracle problem: the challenge of distinguishing correct from incorrect program behavior. With the rise of Foundation Models (FMs), particularly Large Language Models (LLMs), there is a new opportunity to generate test oracles that reflect intended behavior. This positions LLMs as enablers of Promptware, where software creation and testing are driven by natural-language prompts. This paper presents an empirical study on the effectiveness of LLMs in generating test oracles that expose software failures. We investigate how different prompting strategies and levels of contextual input impact the quality of LLM-generated oracles. Our findings offer insights into the strengths and limitations of LLM-based oracle generation in the FM era, improving our understanding of their capabilities and fostering future research in this area.
format Preprint
id arxiv_https___arxiv_org_abs_2601_05542
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Understanding LLM-Driven Test Oracle Generation
Bodicoat, Adam
Jahangirova, Gunel
Terragni, Valerio
Software Engineering
Artificial Intelligence
Machine Learning
Automated unit test generation aims to improve software quality while reducing the time and effort required for creating tests manually. However, existing techniques primarily generate regression oracles that predicate on the implemented behavior of the class under test. They do not address the oracle problem: the challenge of distinguishing correct from incorrect program behavior. With the rise of Foundation Models (FMs), particularly Large Language Models (LLMs), there is a new opportunity to generate test oracles that reflect intended behavior. This positions LLMs as enablers of Promptware, where software creation and testing are driven by natural-language prompts. This paper presents an empirical study on the effectiveness of LLMs in generating test oracles that expose software failures. We investigate how different prompting strategies and levels of contextual input impact the quality of LLM-generated oracles. Our findings offer insights into the strengths and limitations of LLM-based oracle generation in the FM era, improving our understanding of their capabilities and fostering future research in this area.
title Understanding LLM-Driven Test Oracle Generation
topic Software Engineering
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2601.05542