From Code Generation to Software Testing: AI Copilot with Context-Based RAG

2025-04-02

IEEE Software

AI Summary

To address low testing efficiency, insufficient defect detection rates, and limited coverage in large-scale software development, this paper proposes a test-oriented AI Copilot framework. Methodologically, it introduces a test-scenario-specific dynamic context-aware retrieval-augmented generation (RAG) mechanism, integrating LLM fine-tuning, code semantic graph construction, and incremental test-knowledge retrieval to enable real-time co-execution of test case generation and defect detection—synchronized with code evolution. Crucially, it models code generation and defect detection as symbiotic tasks sharing a common “low-defect” objective—the first such formulation. Experimental results demonstrate a 31.2% improvement in bug detection accuracy, a 12.6% increase in critical-path test coverage, and a 10.5% rise in user acceptance rate, validating the framework’s effectiveness in enhancing both automated testing quality and developer productivity.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The rapid pace of large-scale software development places increasing demands on traditional testing methodologies, often leading to bottlenecks in efficiency, accuracy, and coverage. We propose a novel perspective on software testing by positing bug detection and coding with fewer bugs as two interconnected problems that share a common goal, which is reducing bugs with limited resources. We extend our previous work on AI-assisted programming, which supports code auto-completion and chatbot-powered Q&A, to the realm of software testing. We introduce Copilot for Testing, an automated testing system that synchronizes bug detection with codebase updates, leveraging context-based Retrieval Augmented Generation (RAG) to enhance the capabilities of large language models (LLMs). Our evaluation demonstrates a 31.2% improvement in bug detection accuracy, a 12.6% increase in critical test coverage, and a 10.5% higher user acceptance rate, highlighting the transformative potential of AI-driven technologies in modern software development practices.

Problem

• Improving software testing efficiency and accuracy with AI
• Connecting bug detection and coding to reduce software bugs
• Enhancing test coverage and user acceptance via AI Copilot

Innovation

• AI Copilot for automated software testing
• Context-based RAG enhances LLM capabilities
• Synchronizes bug detection with code updates