PRIMG : Efficient LLM-driven Test Generation Using Mutant Prioritization

TL;DR

PRIMG is a framework that combines mutation prioritization with LLM-based test generation to create efficient, high-coverage test suites for Solidity smart contracts, reducing computational costs and improving test quality.

Contribution

This paper introduces PRIMG, a novel framework integrating machine learning-based mutant prioritization with LLM-driven test generation for smart contracts.

Findings

PRIMG reduces test suite size while maintaining high mutation coverage.

The mutant prioritization module outperforms random selection.

Refinement improves the correctness and utility of generated tests.

Abstract

Mutation testing is a widely recognized technique for assessing and enhancing the effectiveness of software test suites by introducing deliberate code mutations. However, its application often results in overly large test suites, as developers generate numerous tests to kill specific mutants, increasing computational overhead. This paper introduces PRIMG (Prioritization and Refinement Integrated Mutation-driven Generation), a novel framework for incremental and adaptive test case generation for Solidity smart contracts. PRIMG integrates two core components: a mutation prioritization module, which employs a machine learning model trained on mutant subsumption graphs to predict the usefulness of surviving mutants, and a test case generation module, which utilizes Large Language Models (LLMs) to generate and iteratively refine test cases to achieve syntactic and behavioral correctness. We evaluated PRIMG on real-world Solidity projects from Code4Arena to assess its effectiveness in improving mutation scores and generating high-quality test cases. The experimental results demonstrate that PRIMG significantly reduces test suite size while maintaining high mutation coverage. The prioritization module consistently outperformed random mutant selection, enabling the generation of high-impact tests with reduced computational effort. Furthermore, the refining process enhanced the correctness and utility of LLM-generated tests, addressing their inherent limitations in handling edge cases and complex program logic.