Intel / article

Repository-Aware Metamorphic Relation Generation for Augmented Reality Applications using Large Language Models

Source: arxiv.org
Author: Dibyendu Brinto Bose, Jiawei Qin, Chris Brown
Date: Published Aug 3, 2026

Context

Testing augmented-reality software is difficult when changing physical surroundings make the exact correct output hard to specify. This study uses language models and repository to propose relationships that should hold between inputs and outputs, providing checks without prescribing every exact result. The pipeline generated 14,916 candidate relationships across 142 repositories and refined conflicting suggestions. Researchers manually examined 141 refined relationships and converted five into executable tests that detected deliberately introduced code changes that altered behavior. Those results support the approach as a way to propose testable rules; executable validation covered only a small subset of the generated candidates.

Key takeaways · AI-distilled

Metamorphic relations sidestep the AR test-oracle problem - dynamic interplay of virtual content, physical environment and code makes exact-output oracles impractical - but writing MRs by hand is the bottleneck this pipeline removes.
Repository-level hierarchical context produced the broadest, least redundant generation: 7,004 candidate MRs across 142 mobile AR repositories and 5,167 class-method pairs.
Conflicting candidate MRs showed up in 79% of cases; an agentic deliberation step reconciles them and picks context-aware relations in 88.2% of outcomes.
Validation: a manual oracle study found refined relations concrete enough to translate directly into test assertions, and converted MRs caught non-equivalent mutations in real-world code.

Terms in this piece · Glossary

context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.

Key quotes

“Metamorphic Testing (MT) provides a promising approach for testing software without defined test oracles by specifying expected relations between inputs and outputs, instead of relying on exact outputs.”

“An agentic deliberation process then reconciled conflicting candidates---observed in 79.0% of cases---reducing duplication and selecting context-aware relations in 88.2% of outcomes.”

Read the source arxiv.org