Automated Unit Test Improvement using Large Language Models at Meta · HackerPapers discussions

Automated Unit Test Improvement using Large Language Models at Meta — mentioned by hiddencost

Wed, 28 Feb 2024 08:30:37 GMT

Your question is posed as a hypothetical, but the problem is already solved... Add a dependency graph of different agents and tools. Use summarization (either selecting subsections or rewriting). Give it a scratch space. Use RAG. Why would it need to load the whole code base into memory? We can build very complex architectures on top of this task that mix LLMs with software. https://arxiv.org/abs/2402.09171 This isn't hypothetical; all of these

Paper and discussion history. A mention is not an endorsement.

Automated Unit Test Improvement using Large Language Models at Meta — mentioned by westurner

Sun, 18 Feb 2024 06:06:27 GMT

"Automated Unit Test Improvement using Large Language Models at Meta" (2024) https://arxiv.org/abs/2402.09171 : > 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 believe this is the first report on industrial scale deployment of LLM-generated code backed by such assurances of code improvement. Coverage-guided…

Paper and discussion history. A mention is not an endorsement.

Automated Unit Test Improvement using Large Language Models at Meta — HN submission

Sat, 17 Feb 2024 03:14:00 GMT

Automated Unit Test Improvement Using Large Language Models at Meta

301 points; 188 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Automated Unit Test Improvement using Large Language Models at Meta — HN submission

Thu, 15 Feb 2024 19:02:05 GMT

Automated Unit Test Improvement Using Large Language Models at Meta

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.