quality_assurance · saas · workflow
Automated Unit Test Improvement using LLMs at Meta — TestGen-LLM
Existing unit tests in Meta's Android/Kotlin applications left edge cases unaddressed, limiting code coverage and requiring manual effort to improve test suites.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · LLM test case generation
LLMs generate additional test cases for existing unit tests to address neglected edge cases.
Tools used
TestGen-LLMLLMs
Outcome
TestGen-LLM enhanced 10% of the classes it was applied to, with most recommendations positively accepted by Meta's software engineers for production, and demonstrated substantial improvements in unit test coverage and code base quality.
Results
Volume10%
Source
https://www.emergentmind.com/assistant/https-arxiv-org-abs-2402-09171/ec12fddf0024cb30c0eb8b9a
Grounding & classification
Source type: technical build writeup
18 fields verified against source quotes.
code generationquality inspectionhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedsoftwareaccuracy improvementautomation ratetechnical build writeupquality assuranceai draft human approval