MAADBench: The Refreshable Paradigm for Anomaly Detection in Multi-Agent Systems
Recent studies report that LLM-based multi-agent systems (MAS) fail at rates of 41%-87%, yet to our knowledge, no benchmark to date supports systematic anomaly detection (AD) for them. Building MAS AD benchmarks is hard because they must remain fresh as LLM systems evolve: tasks may leak into training data and thus be...
Lei Ma, Dennis M. Hofmann, Hao-Wen Xu et al.
· 0 citations