# Meta reported deploying TestGen-LLM at Instagram and Facebook test-a-thons: it improved 11.5% of the classes it was applied to and engineers accepted 73% of its recommended test cases into production

Page: https://flyvolo.ai/en/changes/ev-20240214-software-tester-1
Date: 2024-02-14 · Stage: Pilot
Can this record move a task judgement? only together with another independent record
Occupation: https://flyvolo.ai/en/careers/software-tester

## Scope

One company, improvement of existing unit-test classes with build/pass/coverage filters; 75% of generated cases built, 57% passed reliably, 25% added coverage. Company-authored paper; a time-boxed test-a-thon setting rather than routine pipeline use.

## Source

- Meta — industry paper (arXiv 2402.09171, FSE 2024) — https://arxiv.org/abs/2402.09171 (primary source)

## What this means

A pilot record on the test-case-writing task with the filters shown: at Meta's test-a-thons a generation tool improved 11.5% of the classes it touched and engineers accepted 73% of the cases it recommended, after build, pass and coverage filters removed the rest. It supports the task page's mechanism — tests generated at volume, the human step being accept or reject — while 75% built / 57% passed reliably / 25% added coverage shows how much output is discarded.

## What it does not show yet

This is a time-boxed event at one company with mature test infrastructure, written up by the tool's authors, and the tool extends existing unit-test classes; it does not write tests from requirements, cover integration or end-to-end testing, or run in a routine pipeline. Nothing here shows any change in how many testers Meta or anyone else employs.

## How to verify it yourself

Take one module you test and run whichever generation tool your team can access against its existing unit tests, then record how many generated cases build, pass three times in a row, and add a line of coverage; comparing your three numbers with Meta's 75/57/25 tells you whether your codebase is easier or harder for the tools than theirs.


More: https://flyvolo.ai/llms.txt