GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers",
  "normalized_query": "2604.02648",
  "route": "/paper/gbqa-a-game-benchmark-for-evaluating-llms-as-quality-assurance-engineers",
  "paper_ref": "gbqa-a-game-benchmark-for-evaluating-llms-as-quality-assurance-engineers",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}