EMBERS: Empirically Motivated Robustness Testing of Deep Research Systems via Defect-Guided Fuzzing
This work proposes EMBERS, an empirically motivated, defect-guided fuzzing framework for robustness testing of DR systems, and generates stage-targeted test inputs using defect-guided mutation, web-search-assisted fidelity assurance, and diversity-aware seed maintenance.
Shuo-Chuan Li, Zan Wang, Dong Wang et al.
· 0 citations