{
  "annotation_id": "c57a950a-ff79-4421-9350-11e58377ea84",
  "date_created": "2026-02-17T05:53:04.727000Z",
  "date_modified": "2026-02-17T05:53:04.727000Z",
  "file_hash": "707cc2795606e85a67e0d1acfa8b1592019d5bf6652942ce44aed65128ea16da",
  "private": false,
  "record": {
    "abstract": "Software testing is critical in the software development lifecycle, yet translating requirements into executable test scripts remains manual and error-prone. While Large Language Models (LLMs) can generate code, they often hallucinate non-existent UI elements. We present the Autonomous QA Agent, a Retrieval-Augmented Generation (RAG) system that grounds Selenium script generation in project-specific documentation and HTML structure. By ingesting diverse formats (Markdown, PDF, HTML) into a vector database, our system retrieves relevant context before generation. Evaluation on 20 e-commerce test scenarios shows our RAG approach achieves 100% (20/20) syntax validity and 90% (18/20, 95% CI: [85%, 95%], p \u003c 0.001) execution success, compared to 30% for standard LLM generation. While our evaluation is limited to a single domain, our method significantly reduces hallucinations by grounding generation in actual DOM structure, demonstrating RAG\u0027s potential for automated UI testing.",
    "arxiv_id": "2601.06034",
    "authors": [
      "Dudekula Kasim Vali"
    ],
    "categories": [
      "cs.SE",
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "Autonomous QA Agent: A Retrieval-Augmented Framework for Reliable Selenium Script Generation",
    "url": "https://arxiv.org/abs/2601.06034",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "439a0d7a-c46f-45f0-9ccc-6a680c18183b",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}