X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems
[Sztuczna inteligencja] Autorzy: Yeonsung Jung, Zhiyuan Wang, Zifan Wang i 5 więcej
Personal agents increasingly connect to services across the web and applications by using tools. As the effects of their actions accumulate and interact across services, unintended or harmful outcomes can arise when agents fulfill benign user requests. Proactively identifying these compositional failures requires systematically exploring diverse cross-service paths. Existing red-teaming methods often simply prompt LLMs to identify potentially harmful paths from task and environment descriptions or decompose harmful objectives specified by humans or LLMs into seemingly benign action combinations. However, generation is biased toward patterns learned during training, potentially favoring familiar tool combinations and leaving novel cross-service interactions underexplored. To address this, we propose X-AgentRed, a self-evolving red-teaming framework that discovers harmful tool call paths …
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja