works on
agent evaluation 1benchmark transfer 1dynamic claim-level evaluation 1expert-grounded assessment 1open-ended professional tasks 1

From the 1 of 5 linked papers with an AI index.

collaborators
Showing cs.MAShow all

1 paper · 1 filter

cs.MA2026

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems

Haowen Dai, Zonghao Ying, Wenfeng Li +10

Multi-agent systems improve capability through task decomposition and role specialization, but these same mechanisms introduce an important safety blind spot: a harmful objective c…