Automated Unit Test Improvement using Large Language Models at Meta

TL;DR

Meta's TestGen-LLM leverages large language models to automatically improve human-written tests, successfully increasing coverage and reliability in large-scale industrial deployments at Meta.

Contribution

This work introduces TestGen-LLM, a novel LLM-based tool for automatic test improvement with built-in verification, deployed at Meta's scale for the first time.

Findings

75% of generated test cases built correctly

57% of tests passed reliably

25% increase in test coverage

Abstract

This paper describes Meta's TestGen-LLM tool, which uses LLMs to automatically improve existing human-written tests. TestGen-LLM verifies that its generated test classes successfully clear a set of filters that assure measurable improvement over the original test suite, thereby eliminating problems due to LLM hallucination. We describe the deployment of TestGen-LLM at Meta test-a-thons for the Instagram and Facebook platforms. In an evaluation on Reels and Stories products for Instagram, 75% of TestGen-LLM's test cases built correctly, 57% passed reliably, and 25% increased coverage. During Meta's Instagram and Facebook test-a-thons, it improved 11.5% of all classes to which it was applied, with 73% of its recommendations being accepted for production deployment by Meta software engineers. We believe this is the first report on industrial scale deployment of LLM-generated code backed by such assurances of code improvement.