作者位次 #5/7ACL 2026Findings· Findings of ACL
T opo SHIELD : Reshaping the Flow of Malice via Spatio-Temporal Risk-Aware Topological Evolution in Multi-Agent Systems
Ruiyang Huang · Chenxi Wang · Tinghe Zhang · Fengrui Liu · Jiayan Sun · Haocheng Wang · Yifan Wu
摘要
While LLM-based Multi-Agent Systems (MAS) demonstrate remarkable problem-solving capabilities, their interconnectivity acts as a conduit for the rapid spread of malicious injections. Addressing the limitations of static defenses, we present TopoSHIELD, a framework that reshapes the flow of malice...