An LLM-based agent with screen refinement, structured prompting, back-button recovery, and LoRA distillation executes natural-language Android test cases, reporting 73% success across 390 cases on 10 apps.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
LELANTE: LEveraging LLM for Automated ANdroid TEsting
An LLM-based agent with screen refinement, structured prompting, back-button recovery, and LoRA distillation executes natural-language Android test cases, reporting 73% success across 390 cases on 10 apps.