A multi-agent LLM system with a scenario knowledge graph can automate soap opera testing on Android apps, finding real bugs but with more false positives than manual testing.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Automated Soap Opera Testing Directed by LLMs and Scenario Knowledge: Feasibility, Challenges, and Road Ahead
A multi-agent LLM system with a scenario knowledge graph can automate soap opera testing on Android apps, finding real bugs but with more false positives than manual testing.