Autonomous QA Agent uses RAG to generate reliable Selenium test scripts

Researchers have developed an Autonomous QA Agent, a retrieval-augmented generation (RAG) system designed to improve the reliability of automated software testing scripts. This system grounds Selenium script generation in project-specific documentation and HTML structure, addressing the issue of LLMs hallucinating non-existent UI elements. Evaluations demonstrated a significant improvement in syntax validity and execution success rates compared to standard LLM generation, highlighting the potential of RAG for automated UI testing. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Enhances reliability of automated UI testing by reducing LLM hallucinations through RAG.

RANK_REASON Academic paper detailing a new framework for automated software testing. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Autonomous QA Agent
• Selenium
• Large Language Models
• RAG
• Markdown
• PDF
• HTML
• arXiv

• paper
• product