3 accepted papers
Evaluating security and reliability for multi-agent systems (MAS) is urgent as they become increasingly prevalent in various applications. As an evaluation technique, existing adversarial attack frameworks face certain limitations, e.g., impracticality due to the requirement of white-box information
Tool-calling text-to-image (T2I) agents can plan and execute multi-step tool chains to accomplish complex generation and editing queries. However, this capability introduces a new safety attack surface: harmful outputs may arise from tool orchestration, where individually benign steps combine into u…
Explaining multi-agent systems (MAS) is urgent as these systems become increasingly prevalent in various applications. Previous work has provided explanations for the actions or states of agents, yet falls short in understanding the blackboxed agent’s importance within a MAS and the overall team str…