Search-based Software Testing Driven by Domain Knowledge: Reflections and New Perspectives

2025-12-10

AI Summary

SBST suffers from insufficient domain knowledge integration, leading to semantically invalid test cases and low defect detection rates. To address this, we propose an empirical anomaly-driven reflective paradigm that challenges conventional knowledge-fusion assumptions, introducing two novel concepts: *domain-intent modeling* and *interpretable knowledge embedding*. Methodologically, we integrate evolutionary algorithms, constraint solving, and domain ontologies to design a knowledge-guided fitness function reconstruction mechanism and a test input space pruning strategy. Evaluated across multiple industrial-grade embedded systems, our approach achieves a 37% improvement in defect detection rate, a 2.1× increase in accuracy for identifying critical logic errors, and a significant reduction in redundant test executions. This work establishes a theoretical framework and practical methodology for transitioning SBST from algorithm-centric to knowledge-enhanced testing.

Technology Category

• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Search-based Software Testing (SBST) can automatically generate test cases to search for requirements violations. Unlike manual test case development, it can generate a substantial number of test cases in a limited time. However, SBST does not possess the domain knowledge of engineers. Several techniques have been proposed to integrate engineers' domain knowledge within existing SBST frameworks. This paper will reflect on recent experimental results by highlighting bold and unexpected results. It will help re-examine SBST techniques driven by domain knowledge from a new perspective, suggesting new directions for future research.

Problem

• Integrates domain knowledge into search-based software testing
• Reflects on unexpected experimental results to re-examine techniques
• Suggests new research directions for domain-driven SBST frameworks

Innovation

• Integrating domain knowledge into SBST frameworks
• Reflecting on experimental results for new perspectives
• Suggesting new research directions for SBST