E2EDev is a BDD-grounded benchmark with fine-grained requirements, test scenarios, and an automated pipeline that shows current E2ESD frameworks and LLMs struggle to produce software meeting user needs.
When the user enters ’testuser’ into the username field with data-testid ’username-input’
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
E2Edev: Benchmarking Large Language Models in End-to-End Software Development Task
E2EDev is a BDD-grounded benchmark with fine-grained requirements, test scenarios, and an automated pipeline that shows current E2ESD frameworks and LLMs struggle to produce software meeting user needs.