MAADBench: The Refreshable Paradigm for Anomaly Detection in Multi-Agent Systems
MAADBench is presented, the first refreshable MAS AD benchmark designed for diverse, evolving LLM backbones underlying the agents, and automated provision of cost-free, deterministic step-level labels for fine-grained AD evaluation.
Lei Ma, Dennis M. Hofmann, Hao-Wen Xu et al.
· 0 citations