RealDevWorld, an automated GUI-testing evaluation system, matches human expert judgments (0.92 accuracy, 0.85 correlation) on assessing LLM-generated production-ready software.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
You Don't Know Until You Click:Automated GUI Testing for Production-Ready Software Evaluation
RealDevWorld, an automated GUI-testing evaluation system, matches human expert judgments (0.92 accuracy, 0.85 correlation) on assessing LLM-generated production-ready software.