A multi-agent adversarial evaluation platform with six progressive attack strategies shows that role-playing LLMs degrade under sustained pressure, with automated judging correlating with human ratings.
Security of LLM-based Agents: Attacks, Defenses, and Applications,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Adversarial Stress Testing of Role-Playing Language Agents using Multi-Agent Evaluation
A multi-agent adversarial evaluation platform with six progressive attack strategies shows that role-playing LLMs degrade under sustained pressure, with automated judging correlating with human ratings.