Preprint
Aug 2026
Requirements-Augmented Generation for Trustworthy Acceptance Testing of LLM-Based Software
This paper introduces Requirements-Augmented Generation (REAG), which interprets user intentions by retrieving relevant software requirements, domain knowledge, and personas via adaptive RAG and self-reasoning to generate context-aware test oracles, and introduces a confidence-calibrated cascade judgment, which quantifies verdict reliability via simulated expert agreement.
Fanyu Wang, Chetan Arora, Zhenping Xie et al.
· 0 citations