Preprint
Aug 2026
Adversarial Stress Testing of Role-Playing Language Agents using Multi-Agent Evaluation
This work presents a modular multi-agent platform for adversarially stress-testing RPLAs through structured, multi-turn dialogue and acknowledges potential ethical risks associated with adversarial testing methodologies and emphasize responsible usage for improving AI safety.
Saqib Shouqi, Abdullah Nazly, Januki Wanniarachchi et al.
· 0 citations